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": "9634",
"budget": 4550
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007234",
"normalized_example_id": "ex_007234",
"source_idx": 7234,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5687,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9634",
"budget": 5687
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007234",
"normalized_example_id": "ex_007234",
"source_idx": 7234,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5687,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 1446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007235",
"normalized_example_id": "ex_007235",
"source_idx": 7235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2410,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 1928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007235",
"normalized_example_id": "ex_007235",
"source_idx": 7235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2410,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "48",
"budget": 2410
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007235",
"normalized_example_id": "ex_007235",
"source_idx": 7235,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2410,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3226
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007236",
"normalized_example_id": "ex_007236",
"source_idx": 7236,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5376,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007236",
"normalized_example_id": "ex_007236",
"source_idx": 7236,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5376,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5376
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007236",
"normalized_example_id": "ex_007236",
"source_idx": 7236,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5376,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4970
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007238",
"normalized_example_id": "ex_007238",
"source_idx": 7238,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8283,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007238",
"normalized_example_id": "ex_007238",
"source_idx": 7238,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8283,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8283
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007238",
"normalized_example_id": "ex_007238",
"source_idx": 7238,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8283,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3980
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007240",
"normalized_example_id": "ex_007240",
"source_idx": 7240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6633,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5306
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007240",
"normalized_example_id": "ex_007240",
"source_idx": 7240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6633,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6633
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007240",
"normalized_example_id": "ex_007240",
"source_idx": 7240,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6633,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1246
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007242",
"normalized_example_id": "ex_007242",
"source_idx": 7242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2077,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1662
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007242",
"normalized_example_id": "ex_007242",
"source_idx": 7242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2077,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2077
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007242",
"normalized_example_id": "ex_007242",
"source_idx": 7242,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2077,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{231}{25}",
"budget": 2596
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007246",
"normalized_example_id": "ex_007246",
"source_idx": 7246,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{231}{25}",
"budget": 3462
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007246",
"normalized_example_id": "ex_007246",
"source_idx": 7246,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{231}{25}",
"budget": 4327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007246",
"normalized_example_id": "ex_007246",
"source_idx": 7246,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=\\frac{5 \\times 3^{n+1}-15}{4}-\\frac{n(n+6)}{2}",
"budget": 4429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007249",
"normalized_example_id": "ex_007249",
"source_idx": 7249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7382,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=\\frac{5 \\times 3^{n+1}-15}{4}-\\frac{n(n+6)}{2}",
"budget": 5906
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007249",
"normalized_example_id": "ex_007249",
"source_idx": 7249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7382,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n}=\\frac{5 \\times 3^{n+1}-15}{4}-\\frac{n(n+6)}{2}",
"budget": 7382
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007249",
"normalized_example_id": "ex_007249",
"source_idx": 7249,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7382,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1672
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007250",
"normalized_example_id": "ex_007250",
"source_idx": 7250,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2229
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007250",
"normalized_example_id": "ex_007250",
"source_idx": 7250,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2786
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007250",
"normalized_example_id": "ex_007250",
"source_idx": 7250,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2786,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(-2)-6)(f(2)-14)=1",
"budget": 3303
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007251",
"normalized_example_id": "ex_007251",
"source_idx": 7251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5505,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(-2)-6)(f(2)-14)=1",
"budget": 4404
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007251",
"normalized_example_id": "ex_007251",
"source_idx": 7251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5505,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(-2)-6)(f(2)-14)=1",
"budget": 5505
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007251",
"normalized_example_id": "ex_007251",
"source_idx": 7251,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5505,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4156
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007256",
"normalized_example_id": "ex_007256",
"source_idx": 7256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6926,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5541
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007256",
"normalized_example_id": "ex_007256",
"source_idx": 7256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6926,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6926
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007256",
"normalized_example_id": "ex_007256",
"source_idx": 7256,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6926,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 700
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007257",
"normalized_example_id": "ex_007257",
"source_idx": 7257,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1166,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 933
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007257",
"normalized_example_id": "ex_007257",
"source_idx": 7257,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1166,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 1166
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007257",
"normalized_example_id": "ex_007257",
"source_idx": 7257,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1166,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "341",
"budget": 4136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007258",
"normalized_example_id": "ex_007258",
"source_idx": 7258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6894,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "341",
"budget": 5515
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007258",
"normalized_example_id": "ex_007258",
"source_idx": 7258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6894,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "341",
"budget": 6894
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007258",
"normalized_example_id": "ex_007258",
"source_idx": 7258,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6894,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-1)^{n}}{n^{n-1}}",
"budget": 974
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007259",
"normalized_example_id": "ex_007259",
"source_idx": 7259,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-1)^{n}}{n^{n-1}}",
"budget": 1298
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007259",
"normalized_example_id": "ex_007259",
"source_idx": 7259,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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-1)^{n}}{n^{n-1}}",
"budget": 1623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007259",
"normalized_example_id": "ex_007259",
"source_idx": 7259,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 896
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007260",
"normalized_example_id": "ex_007260",
"source_idx": 7260,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1194
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007260",
"normalized_example_id": "ex_007260",
"source_idx": 7260,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1493
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007260",
"normalized_example_id": "ex_007260",
"source_idx": 7260,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1493,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{67}{20}",
"budget": 1463
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007261",
"normalized_example_id": "ex_007261",
"source_idx": 7261,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2439,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{67}{20}",
"budget": 1951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007261",
"normalized_example_id": "ex_007261",
"source_idx": 7261,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2439,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{67}{20}",
"budget": 2439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007261",
"normalized_example_id": "ex_007261",
"source_idx": 7261,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2439,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(45,2)",
"budget": 2497
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007270",
"normalized_example_id": "ex_007270",
"source_idx": 7270,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4161,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(45,2)",
"budget": 3329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007270",
"normalized_example_id": "ex_007270",
"source_idx": 7270,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4161,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(45,2)",
"budget": 4161
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007270",
"normalized_example_id": "ex_007270",
"source_idx": 7270,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4161,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "55",
"budget": 1570
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007271",
"normalized_example_id": "ex_007271",
"source_idx": 7271,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2617,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "55",
"budget": 2094
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007271",
"normalized_example_id": "ex_007271",
"source_idx": 7271,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2617,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "55",
"budget": 2617
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007271",
"normalized_example_id": "ex_007271",
"source_idx": 7271,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2617,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 3322
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007272",
"normalized_example_id": "ex_007272",
"source_idx": 7272,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 4429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007272",
"normalized_example_id": "ex_007272",
"source_idx": 7272,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 5536
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007272",
"normalized_example_id": "ex_007272",
"source_idx": 7272,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5536,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.7",
"budget": 1284
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007274",
"normalized_example_id": "ex_007274",
"source_idx": 7274,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2140,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.7",
"budget": 1712
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007274",
"normalized_example_id": "ex_007274",
"source_idx": 7274,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2140,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.7",
"budget": 2140
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007274",
"normalized_example_id": "ex_007274",
"source_idx": 7274,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2140,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "BP:PK=1,AP:PM=3:1",
"budget": 2324
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007276",
"normalized_example_id": "ex_007276",
"source_idx": 7276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "BP:PK=1,AP:PM=3:1",
"budget": 3099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007276",
"normalized_example_id": "ex_007276",
"source_idx": 7276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "BP:PK=1,AP:PM=3:1",
"budget": 3874
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007276",
"normalized_example_id": "ex_007276",
"source_idx": 7276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "182",
"budget": 1056
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007278",
"normalized_example_id": "ex_007278",
"source_idx": 7278,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1760,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "182",
"budget": 1408
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007278",
"normalized_example_id": "ex_007278",
"source_idx": 7278,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1760,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "182",
"budget": 1760
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007278",
"normalized_example_id": "ex_007278",
"source_idx": 7278,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1760,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3537
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007279",
"normalized_example_id": "ex_007279",
"source_idx": 7279,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5895,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4716
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007279",
"normalized_example_id": "ex_007279",
"source_idx": 7279,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5895,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5895
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007279",
"normalized_example_id": "ex_007279",
"source_idx": 7279,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5895,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3024",
"budget": 2719
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007281",
"normalized_example_id": "ex_007281",
"source_idx": 7281,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4532,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3024",
"budget": 3626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007281",
"normalized_example_id": "ex_007281",
"source_idx": 7281,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4532,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3024",
"budget": 4532
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007281",
"normalized_example_id": "ex_007281",
"source_idx": 7281,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4532,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30^\\circ",
"budget": 2738
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007283",
"normalized_example_id": "ex_007283",
"source_idx": 7283,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4564,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30^\\circ",
"budget": 3651
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007283",
"normalized_example_id": "ex_007283",
"source_idx": 7283,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4564,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30^\\circ",
"budget": 4564
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007283",
"normalized_example_id": "ex_007283",
"source_idx": 7283,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4564,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{10}",
"budget": 4666
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007284",
"normalized_example_id": "ex_007284",
"source_idx": 7284,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7777,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{10}",
"budget": 6222
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007284",
"normalized_example_id": "ex_007284",
"source_idx": 7284,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7777,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{10}",
"budget": 7777
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007284",
"normalized_example_id": "ex_007284",
"source_idx": 7284,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7777,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "200",
"budget": 4636
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007286",
"normalized_example_id": "ex_007286",
"source_idx": 7286,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7727,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "200",
"budget": 6182
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007286",
"normalized_example_id": "ex_007286",
"source_idx": 7286,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7727,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "200",
"budget": 7727
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007286",
"normalized_example_id": "ex_007286",
"source_idx": 7286,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7727,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5113
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007287",
"normalized_example_id": "ex_007287",
"source_idx": 7287,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8522,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6818
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007287",
"normalized_example_id": "ex_007287",
"source_idx": 7287,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8522,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 8522
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007287",
"normalized_example_id": "ex_007287",
"source_idx": 7287,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8522,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "77",
"budget": 1629
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007289",
"normalized_example_id": "ex_007289",
"source_idx": 7289,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "77",
"budget": 2172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007289",
"normalized_example_id": "ex_007289",
"source_idx": 7289,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "77",
"budget": 2715
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007289",
"normalized_example_id": "ex_007289",
"source_idx": 7289,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2715,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,5,19,37),(2,11,19,31),(2,13,19,29)",
"budget": 6122
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007292",
"normalized_example_id": "ex_007292",
"source_idx": 7292,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10203,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,5,19,37),(2,11,19,31),(2,13,19,29)",
"budget": 8162
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007292",
"normalized_example_id": "ex_007292",
"source_idx": 7292,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10203,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(2,5,19,37),(2,11,19,31),(2,13,19,29)",
"budget": 10203
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007292",
"normalized_example_id": "ex_007292",
"source_idx": 7292,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10203,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "65",
"budget": 1543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007294",
"normalized_example_id": "ex_007294",
"source_idx": 7294,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2571,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "65",
"budget": 2057
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007294",
"normalized_example_id": "ex_007294",
"source_idx": 7294,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2571,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "65",
"budget": 2571
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007294",
"normalized_example_id": "ex_007294",
"source_idx": 7294,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2571,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 1747
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007296",
"normalized_example_id": "ex_007296",
"source_idx": 7296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2911,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 2329
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007296",
"normalized_example_id": "ex_007296",
"source_idx": 7296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2911,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "D",
"budget": 2911
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007296",
"normalized_example_id": "ex_007296",
"source_idx": 7296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2911,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{12}{11}",
"budget": 719
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007298",
"normalized_example_id": "ex_007298",
"source_idx": 7298,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1198,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{12}{11}",
"budget": 958
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007298",
"normalized_example_id": "ex_007298",
"source_idx": 7298,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1198,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{12}{11}",
"budget": 1198
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007298",
"normalized_example_id": "ex_007298",
"source_idx": 7298,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1198,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\bar{\\lambda}\\omega+\\bar{\\omega}}{1-|\\lambda|^{2}}",
"budget": 3136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007299",
"normalized_example_id": "ex_007299",
"source_idx": 7299,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\bar{\\lambda}\\omega+\\bar{\\omega}}{1-|\\lambda|^{2}}",
"budget": 4182
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_007299",
"normalized_example_id": "ex_007299",
"source_idx": 7299,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5227,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.