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": "\\frac{2}{9}",
"budget": 3454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002127",
"normalized_example_id": "ex_002127",
"source_idx": 2127,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{2}{9}",
"budget": 4317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002127",
"normalized_example_id": "ex_002127",
"source_idx": 2127,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{125(2+\\sqrt{5})}{64}",
"budget": 2571
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002128",
"normalized_example_id": "ex_002128",
"source_idx": 2128,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{125(2+\\sqrt{5})}{64}",
"budget": 3428
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002128",
"normalized_example_id": "ex_002128",
"source_idx": 2128,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{125(2+\\sqrt{5})}{64}",
"budget": 4285
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002128",
"normalized_example_id": "ex_002128",
"source_idx": 2128,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4285,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4044",
"budget": 2210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002129",
"normalized_example_id": "ex_002129",
"source_idx": 2129,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3684,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4044",
"budget": 2947
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002129",
"normalized_example_id": "ex_002129",
"source_idx": 2129,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3684,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4044",
"budget": 3684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002129",
"normalized_example_id": "ex_002129",
"source_idx": 2129,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3684,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 2978
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002134",
"normalized_example_id": "ex_002134",
"source_idx": 2134,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4963,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 3970
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002134",
"normalized_example_id": "ex_002134",
"source_idx": 2134,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4963,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 4963
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002134",
"normalized_example_id": "ex_002134",
"source_idx": 2134,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4963,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+y=0",
"budget": 1331
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002135",
"normalized_example_id": "ex_002135",
"source_idx": 2135,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+y=0",
"budget": 1775
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002135",
"normalized_example_id": "ex_002135",
"source_idx": 2135,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+y=0",
"budget": 2219
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002135",
"normalized_example_id": "ex_002135",
"source_idx": 2135,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2219,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 4318
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002136",
"normalized_example_id": "ex_002136",
"source_idx": 2136,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7196,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 5757
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002136",
"normalized_example_id": "ex_002136",
"source_idx": 2136,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7196,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 7196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002136",
"normalized_example_id": "ex_002136",
"source_idx": 2136,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7196,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2048",
"budget": 4374
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002138",
"normalized_example_id": "ex_002138",
"source_idx": 2138,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7290,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2048",
"budget": 5832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002138",
"normalized_example_id": "ex_002138",
"source_idx": 2138,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7290,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2048",
"budget": 7290
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002138",
"normalized_example_id": "ex_002138",
"source_idx": 2138,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7290,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4\\sqrt{3}}{3}",
"budget": 2351
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002139",
"normalized_example_id": "ex_002139",
"source_idx": 2139,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3918,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4\\sqrt{3}}{3}",
"budget": 3134
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002139",
"normalized_example_id": "ex_002139",
"source_idx": 2139,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3918,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4\\sqrt{3}}{3}",
"budget": 3918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002139",
"normalized_example_id": "ex_002139",
"source_idx": 2139,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3918,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12453",
"budget": 5978
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002140",
"normalized_example_id": "ex_002140",
"source_idx": 2140,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9963,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12453",
"budget": 7970
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002140",
"normalized_example_id": "ex_002140",
"source_idx": 2140,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9963,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12453",
"budget": 9963
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002140",
"normalized_example_id": "ex_002140",
"source_idx": 2140,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9963,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4:3",
"budget": 3736
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002141",
"normalized_example_id": "ex_002141",
"source_idx": 2141,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4:3",
"budget": 4982
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002141",
"normalized_example_id": "ex_002141",
"source_idx": 2141,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4:3",
"budget": 6227
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002141",
"normalized_example_id": "ex_002141",
"source_idx": 2141,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3226
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002142",
"normalized_example_id": "ex_002142",
"source_idx": 2142,
"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": "D",
"budget": 4301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002142",
"normalized_example_id": "ex_002142",
"source_idx": 2142,
"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": "D",
"budget": 5376
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002142",
"normalized_example_id": "ex_002142",
"source_idx": 2142,
"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": "-1",
"budget": 1124
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002143",
"normalized_example_id": "ex_002143",
"source_idx": 2143,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1499
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002143",
"normalized_example_id": "ex_002143",
"source_idx": 2143,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1874
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002143",
"normalized_example_id": "ex_002143",
"source_idx": 2143,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1874,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)=xy",
"budget": 3983
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002144",
"normalized_example_id": "ex_002144",
"source_idx": 2144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)=xy",
"budget": 5311
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002144",
"normalized_example_id": "ex_002144",
"source_idx": 2144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,y)=xy",
"budget": 6639
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002144",
"normalized_example_id": "ex_002144",
"source_idx": 2144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6639,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2852
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002145",
"normalized_example_id": "ex_002145",
"source_idx": 2145,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4753,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3802
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002145",
"normalized_example_id": "ex_002145",
"source_idx": 2145,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4753,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4753
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002145",
"normalized_example_id": "ex_002145",
"source_idx": 2145,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4753,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{32}",
"budget": 5485
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002149",
"normalized_example_id": "ex_002149",
"source_idx": 2149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9141,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{32}",
"budget": 7313
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002149",
"normalized_example_id": "ex_002149",
"source_idx": 2149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9141,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{32}",
"budget": 9141
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002149",
"normalized_example_id": "ex_002149",
"source_idx": 2149,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9141,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\geqq\\frac{1}{1000}",
"budget": 850
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002160",
"normalized_example_id": "ex_002160",
"source_idx": 2160,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1417,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\geqq\\frac{1}{1000}",
"budget": 1134
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002160",
"normalized_example_id": "ex_002160",
"source_idx": 2160,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1417,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\geqq\\frac{1}{1000}",
"budget": 1417
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002160",
"normalized_example_id": "ex_002160",
"source_idx": 2160,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1417,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{8}",
"budget": 2272
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002161",
"normalized_example_id": "ex_002161",
"source_idx": 2161,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{8}",
"budget": 3030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002161",
"normalized_example_id": "ex_002161",
"source_idx": 2161,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5}{8}",
"budget": 3787
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002161",
"normalized_example_id": "ex_002161",
"source_idx": 2161,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3787,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3030
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002162",
"normalized_example_id": "ex_002162",
"source_idx": 2162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5050,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4040
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002162",
"normalized_example_id": "ex_002162",
"source_idx": 2162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5050,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5050
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002162",
"normalized_example_id": "ex_002162",
"source_idx": 2162,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5050,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9 \\sqrt{3}}{4}",
"budget": 2977
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002163",
"normalized_example_id": "ex_002163",
"source_idx": 2163,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4962,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9 \\sqrt{3}}{4}",
"budget": 3970
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002163",
"normalized_example_id": "ex_002163",
"source_idx": 2163,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4962,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{9 \\sqrt{3}}{4}",
"budget": 4962
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002163",
"normalized_example_id": "ex_002163",
"source_idx": 2163,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4962,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,5), (0,4), (5,1)",
"budget": 5984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002165",
"normalized_example_id": "ex_002165",
"source_idx": 2165,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9974,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,5), (0,4), (5,1)",
"budget": 7979
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002165",
"normalized_example_id": "ex_002165",
"source_idx": 2165,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9974,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,5), (0,4), (5,1)",
"budget": 9974
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002165",
"normalized_example_id": "ex_002165",
"source_idx": 2165,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9974,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{3}}{4}",
"budget": 1592
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002167",
"normalized_example_id": "ex_002167",
"source_idx": 2167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2653,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{3}}{4}",
"budget": 2122
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002167",
"normalized_example_id": "ex_002167",
"source_idx": 2167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2653,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{3}}{4}",
"budget": 2653
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002167",
"normalized_example_id": "ex_002167",
"source_idx": 2167,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2653,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{15}",
"budget": 3925
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002168",
"normalized_example_id": "ex_002168",
"source_idx": 2168,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6542,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{15}",
"budget": 5234
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002168",
"normalized_example_id": "ex_002168",
"source_idx": 2168,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6542,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{15}",
"budget": 6542
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002168",
"normalized_example_id": "ex_002168",
"source_idx": 2168,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6542,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1854
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002172",
"normalized_example_id": "ex_002172",
"source_idx": 2172,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3090,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2472
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002172",
"normalized_example_id": "ex_002172",
"source_idx": 2172,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3090,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3090
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002172",
"normalized_example_id": "ex_002172",
"source_idx": 2172,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3090,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "409051",
"budget": 2242
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002174",
"normalized_example_id": "ex_002174",
"source_idx": 2174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3737,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "409051",
"budget": 2990
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002174",
"normalized_example_id": "ex_002174",
"source_idx": 2174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3737,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "409051",
"budget": 3737
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002174",
"normalized_example_id": "ex_002174",
"source_idx": 2174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3737,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 2131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002175",
"normalized_example_id": "ex_002175",
"source_idx": 2175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 2841
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002175",
"normalized_example_id": "ex_002175",
"source_idx": 2175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 3551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002175",
"normalized_example_id": "ex_002175",
"source_idx": 2175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,4,6",
"budget": 3947
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002176",
"normalized_example_id": "ex_002176",
"source_idx": 2176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6578,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,4,6",
"budget": 5262
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002176",
"normalized_example_id": "ex_002176",
"source_idx": 2176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6578,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2,4,6",
"budget": 6578
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002176",
"normalized_example_id": "ex_002176",
"source_idx": 2176,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6578,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, \\sqrt{2}",
"budget": 3155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002178",
"normalized_example_id": "ex_002178",
"source_idx": 2178,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5259,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, \\sqrt{2}",
"budget": 4207
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002178",
"normalized_example_id": "ex_002178",
"source_idx": 2178,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5259,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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, \\sqrt{2}",
"budget": 5259
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002178",
"normalized_example_id": "ex_002178",
"source_idx": 2178,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5259,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 5450
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002180",
"normalized_example_id": "ex_002180",
"source_idx": 2180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 7266
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002180",
"normalized_example_id": "ex_002180",
"source_idx": 2180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 9083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002180",
"normalized_example_id": "ex_002180",
"source_idx": 2180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9083,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2/\\pi}",
"budget": 4373
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002181",
"normalized_example_id": "ex_002181",
"source_idx": 2181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2/\\pi}",
"budget": 5830
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002181",
"normalized_example_id": "ex_002181",
"source_idx": 2181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2/\\pi}",
"budget": 7288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002181",
"normalized_example_id": "ex_002181",
"source_idx": 2181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{5}}{4}",
"budget": 2353
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002184",
"normalized_example_id": "ex_002184",
"source_idx": 2184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3921,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{5}}{4}",
"budget": 3137
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002184",
"normalized_example_id": "ex_002184",
"source_idx": 2184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3921,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{5}}{4}",
"budget": 3921
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002184",
"normalized_example_id": "ex_002184",
"source_idx": 2184,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3921,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "115",
"budget": 2774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002187",
"normalized_example_id": "ex_002187",
"source_idx": 2187,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "115",
"budget": 3698
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002187",
"normalized_example_id": "ex_002187",
"source_idx": 2187,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "115",
"budget": 4623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002187",
"normalized_example_id": "ex_002187",
"source_idx": 2187,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{k+1}=x_{k+2}=\\cdots=x_{n}=\\sqrt{\\frac{A}{B}}",
"budget": 2679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002188",
"normalized_example_id": "ex_002188",
"source_idx": 2188,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4465,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{k+1}=x_{k+2}=\\cdots=x_{n}=\\sqrt{\\frac{A}{B}}",
"budget": 3572
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002188",
"normalized_example_id": "ex_002188",
"source_idx": 2188,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4465,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{k+1}=x_{k+2}=\\cdots=x_{n}=\\sqrt{\\frac{A}{B}}",
"budget": 4465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002188",
"normalized_example_id": "ex_002188",
"source_idx": 2188,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4465,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "Yes",
"budget": 1819
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002190",
"normalized_example_id": "ex_002190",
"source_idx": 2190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3031,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "Yes",
"budget": 2425
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002190",
"normalized_example_id": "ex_002190",
"source_idx": 2190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3031,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "Yes",
"budget": 3031
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002190",
"normalized_example_id": "ex_002190",
"source_idx": 2190,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3031,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002192",
"normalized_example_id": "ex_002192",
"source_idx": 2192,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 3546
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002192",
"normalized_example_id": "ex_002192",
"source_idx": 2192,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4433,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.