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": "9",
"budget": 4435
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000396",
"normalized_example_id": "ex_000396",
"source_idx": 396,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7392,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 5914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000396",
"normalized_example_id": "ex_000396",
"source_idx": 396,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7392,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 7392
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000396",
"normalized_example_id": "ex_000396",
"source_idx": 396,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7392,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{60}{\\sqrt{769}}",
"budget": 5299
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000397",
"normalized_example_id": "ex_000397",
"source_idx": 397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8832,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{60}{\\sqrt{769}}",
"budget": 7066
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000397",
"normalized_example_id": "ex_000397",
"source_idx": 397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8832,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{60}{\\sqrt{769}}",
"budget": 8832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000397",
"normalized_example_id": "ex_000397",
"source_idx": 397,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8832,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16\\pi}{3}+4\\sqrt{3}",
"budget": 2707
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000398",
"normalized_example_id": "ex_000398",
"source_idx": 398,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4512,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16\\pi}{3}+4\\sqrt{3}",
"budget": 3610
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000398",
"normalized_example_id": "ex_000398",
"source_idx": 398,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4512,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{16\\pi}{3}+4\\sqrt{3}",
"budget": 4512
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000398",
"normalized_example_id": "ex_000398",
"source_idx": 398,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4512,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "101",
"budget": 4892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000399",
"normalized_example_id": "ex_000399",
"source_idx": 399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8153,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "101",
"budget": 6522
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000399",
"normalized_example_id": "ex_000399",
"source_idx": 399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8153,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "101",
"budget": 8153
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000399",
"normalized_example_id": "ex_000399",
"source_idx": 399,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8153,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{n\\left(2 n^{2}+1\\right)}{3}}",
"budget": 4890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000400",
"normalized_example_id": "ex_000400",
"source_idx": 400,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8150,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{n\\left(2 n^{2}+1\\right)}{3}}",
"budget": 6520
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000400",
"normalized_example_id": "ex_000400",
"source_idx": 400,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8150,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{\\frac{n\\left(2 n^{2}+1\\right)}{3}}",
"budget": 8150
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000400",
"normalized_example_id": "ex_000400",
"source_idx": 400,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8150,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1054",
"budget": 1834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000401",
"normalized_example_id": "ex_000401",
"source_idx": 401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3057,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1054",
"budget": 2446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000401",
"normalized_example_id": "ex_000401",
"source_idx": 401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3057,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1054",
"budget": 3057
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000401",
"normalized_example_id": "ex_000401",
"source_idx": 401,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3057,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52.5",
"budget": 3081
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000403",
"normalized_example_id": "ex_000403",
"source_idx": 403,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5135,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52.5",
"budget": 4108
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000403",
"normalized_example_id": "ex_000403",
"source_idx": 403,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5135,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52.5",
"budget": 5135
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000403",
"normalized_example_id": "ex_000403",
"source_idx": 403,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5135,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000404",
"normalized_example_id": "ex_000404",
"source_idx": 404,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1296,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 1037
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000404",
"normalized_example_id": "ex_000404",
"source_idx": 404,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1296,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 1296
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000404",
"normalized_example_id": "ex_000404",
"source_idx": 404,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1296,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}",
"budget": 5813
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000405",
"normalized_example_id": "ex_000405",
"source_idx": 405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9689,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}",
"budget": 7751
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000405",
"normalized_example_id": "ex_000405",
"source_idx": 405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9689,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{4}",
"budget": 9689
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000405",
"normalized_example_id": "ex_000405",
"source_idx": 405,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9689,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4906
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000407",
"normalized_example_id": "ex_000407",
"source_idx": 407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8177,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6542
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000407",
"normalized_example_id": "ex_000407",
"source_idx": 407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8177,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8177
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000407",
"normalized_example_id": "ex_000407",
"source_idx": 407,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8177,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "96",
"budget": 4977
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000408",
"normalized_example_id": "ex_000408",
"source_idx": 408,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8295,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "96",
"budget": 6636
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000408",
"normalized_example_id": "ex_000408",
"source_idx": 408,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8295,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "96",
"budget": 8295
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000408",
"normalized_example_id": "ex_000408",
"source_idx": 408,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8295,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2004",
"budget": 5971
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000415",
"normalized_example_id": "ex_000415",
"source_idx": 415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9952,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2004",
"budget": 7962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000415",
"normalized_example_id": "ex_000415",
"source_idx": 415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9952,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2004",
"budget": 9952
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000415",
"normalized_example_id": "ex_000415",
"source_idx": 415,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9952,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "683",
"budget": 4477
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000417",
"normalized_example_id": "ex_000417",
"source_idx": 417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7462,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "683",
"budget": 5970
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000417",
"normalized_example_id": "ex_000417",
"source_idx": 417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7462,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "683",
"budget": 7462
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000417",
"normalized_example_id": "ex_000417",
"source_idx": 417,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7462,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 5314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000420",
"normalized_example_id": "ex_000420",
"source_idx": 420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8857,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 7086
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000420",
"normalized_example_id": "ex_000420",
"source_idx": 420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8857,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "18",
"budget": 8857
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000420",
"normalized_example_id": "ex_000420",
"source_idx": 420,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8857,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3^{201}+1}{4\\cdot3^{201}}",
"budget": 4309
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000424",
"normalized_example_id": "ex_000424",
"source_idx": 424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7181,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3^{201}+1}{4\\cdot3^{201}}",
"budget": 5745
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000424",
"normalized_example_id": "ex_000424",
"source_idx": 424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7181,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3^{201}+1}{4\\cdot3^{201}}",
"budget": 7181
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000424",
"normalized_example_id": "ex_000424",
"source_idx": 424,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7181,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_0 = 0, A_1 = \\frac{1}{\\pi} \\int_0^{2\\pi} f(x) \\cos x \\, dx, B_1 = \\frac{1}{\\pi} \\int_0^{2\\pi} f(x) \\sin x \\, dx",
"budget": 1373
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000425",
"normalized_example_id": "ex_000425",
"source_idx": 425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2289,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_0 = 0, A_1 = \\frac{1}{\\pi} \\int_0^{2\\pi} f(x) \\cos x \\, dx, B_1 = \\frac{1}{\\pi} \\int_0^{2\\pi} f(x) \\sin x \\, dx",
"budget": 1831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000425",
"normalized_example_id": "ex_000425",
"source_idx": 425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2289,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_0 = 0, A_1 = \\frac{1}{\\pi} \\int_0^{2\\pi} f(x) \\cos x \\, dx, B_1 = \\frac{1}{\\pi} \\int_0^{2\\pi} f(x) \\sin x \\, dx",
"budget": 2289
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000425",
"normalized_example_id": "ex_000425",
"source_idx": 425,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2289,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900",
"budget": 1940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000426",
"normalized_example_id": "ex_000426",
"source_idx": 426,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3233,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900",
"budget": 2586
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000426",
"normalized_example_id": "ex_000426",
"source_idx": 426,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3233,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900",
"budget": 3233
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000426",
"normalized_example_id": "ex_000426",
"source_idx": 426,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3233,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 4807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000427",
"normalized_example_id": "ex_000427",
"source_idx": 427,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8011,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 6409
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000427",
"normalized_example_id": "ex_000427",
"source_idx": 427,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8011,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 8011
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000427",
"normalized_example_id": "ex_000427",
"source_idx": 427,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8011,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n=\\frac{(\\sqrt{2}+1)^{2 m}+(\\sqrt{2}-1)^{2 m}-2}{4}\\left(m \\in \\mathbf{N}_{+}\\right)",
"budget": 3590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000429",
"normalized_example_id": "ex_000429",
"source_idx": 429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5983,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n=\\frac{(\\sqrt{2}+1)^{2 m}+(\\sqrt{2}-1)^{2 m}-2}{4}\\left(m \\in \\mathbf{N}_{+}\\right)",
"budget": 4786
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000429",
"normalized_example_id": "ex_000429",
"source_idx": 429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5983,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "n=\\frac{(\\sqrt{2}+1)^{2 m}+(\\sqrt{2}-1)^{2 m}-2}{4}\\left(m \\in \\mathbf{N}_{+}\\right)",
"budget": 5983
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000429",
"normalized_example_id": "ex_000429",
"source_idx": 429,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5983,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[-\\pi,2-\\pi]",
"budget": 955
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000432",
"normalized_example_id": "ex_000432",
"source_idx": 432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1592,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[-\\pi,2-\\pi]",
"budget": 1274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000432",
"normalized_example_id": "ex_000432",
"source_idx": 432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1592,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "[-\\pi,2-\\pi]",
"budget": 1592
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000432",
"normalized_example_id": "ex_000432",
"source_idx": 432,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1592,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70^{\\circ}",
"budget": 2744
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000434",
"normalized_example_id": "ex_000434",
"source_idx": 434,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4573,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70^{\\circ}",
"budget": 3658
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000434",
"normalized_example_id": "ex_000434",
"source_idx": 434,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4573,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "70^{\\circ}",
"budget": 4573
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000434",
"normalized_example_id": "ex_000434",
"source_idx": 434,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4573,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+3\\sqrt{2}",
"budget": 4166
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000435",
"normalized_example_id": "ex_000435",
"source_idx": 435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6944,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+3\\sqrt{2}",
"budget": 5555
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000435",
"normalized_example_id": "ex_000435",
"source_idx": 435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6944,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+3\\sqrt{2}",
"budget": 6944
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000435",
"normalized_example_id": "ex_000435",
"source_idx": 435,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6944,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2303
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000437",
"normalized_example_id": "ex_000437",
"source_idx": 437,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3838,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000437",
"normalized_example_id": "ex_000437",
"source_idx": 437,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3838,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3838
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000437",
"normalized_example_id": "ex_000437",
"source_idx": 437,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3838,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 0, 4",
"budget": 2739
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000441",
"normalized_example_id": "ex_000441",
"source_idx": 441,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4565,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 0, 4",
"budget": 3652
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000441",
"normalized_example_id": "ex_000441",
"source_idx": 441,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4565,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 0, 4",
"budget": 4565
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000441",
"normalized_example_id": "ex_000441",
"source_idx": 441,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4565,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 1583
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000443",
"normalized_example_id": "ex_000443",
"source_idx": 443,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2638,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 2110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000443",
"normalized_example_id": "ex_000443",
"source_idx": 443,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2638,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "6",
"budget": 2638
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000443",
"normalized_example_id": "ex_000443",
"source_idx": 443,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2638,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4499
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000445",
"normalized_example_id": "ex_000445",
"source_idx": 445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7499,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5999
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000445",
"normalized_example_id": "ex_000445",
"source_idx": 445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7499,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7499
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000445",
"normalized_example_id": "ex_000445",
"source_idx": 445,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7499,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sinxy=C",
"budget": 1159
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000446",
"normalized_example_id": "ex_000446",
"source_idx": 446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1932,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sinxy=C",
"budget": 1546
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000446",
"normalized_example_id": "ex_000446",
"source_idx": 446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1932,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sinxy=C",
"budget": 1932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000446",
"normalized_example_id": "ex_000446",
"source_idx": 446,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1932,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1646,3646,6494,8161",
"budget": 2484
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000447",
"normalized_example_id": "ex_000447",
"source_idx": 447,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4140,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1646,3646,6494,8161",
"budget": 3312
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000447",
"normalized_example_id": "ex_000447",
"source_idx": 447,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4140,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1646,3646,6494,8161",
"budget": 4140
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000447",
"normalized_example_id": "ex_000447",
"source_idx": 447,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4140,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^3+xc",
"budget": 4198
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000451",
"normalized_example_id": "ex_000451",
"source_idx": 451,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6996,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^3+xc",
"budget": 5597
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000451",
"normalized_example_id": "ex_000451",
"source_idx": 451,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6996,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^3+xc",
"budget": 6996
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000451",
"normalized_example_id": "ex_000451",
"source_idx": 451,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6996,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\text{ and } 6",
"budget": 5393
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000453",
"normalized_example_id": "ex_000453",
"source_idx": 453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8988,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5 \\text{ and } 6",
"budget": 7190
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000453",
"normalized_example_id": "ex_000453",
"source_idx": 453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8988,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5 \\text{ and } 6",
"budget": 8988
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000453",
"normalized_example_id": "ex_000453",
"source_idx": 453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8988,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1",
"budget": 4808
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000457",
"normalized_example_id": "ex_000457",
"source_idx": 457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8013,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6410
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000457",
"normalized_example_id": "ex_000457",
"source_idx": 457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8013,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000457",
"normalized_example_id": "ex_000457",
"source_idx": 457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8013,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11x",
"budget": 1088
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000458",
"normalized_example_id": "ex_000458",
"source_idx": 458,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1814,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11x",
"budget": 1451
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000458",
"normalized_example_id": "ex_000458",
"source_idx": 458,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1814,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11x",
"budget": 1814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000458",
"normalized_example_id": "ex_000458",
"source_idx": 458,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1814,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4388
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000459",
"normalized_example_id": "ex_000459",
"source_idx": 459,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7313,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5850
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000459",
"normalized_example_id": "ex_000459",
"source_idx": 459,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7313,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7313
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000459",
"normalized_example_id": "ex_000459",
"source_idx": 459,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7313,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000460",
"normalized_example_id": "ex_000460",
"source_idx": 460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2677,
"... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.