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": "39",
"budget": 6164
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002509",
"normalized_example_id": "ex_002509",
"source_idx": 2509,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7705,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "39",
"budget": 7705
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002509",
"normalized_example_id": "ex_002509",
"source_idx": 2509,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7705,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi(x)=1+\\frac{x^{2}}{2}",
"budget": 3043
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002510",
"normalized_example_id": "ex_002510",
"source_idx": 2510,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5072,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi(x)=1+\\frac{x^{2}}{2}",
"budget": 4058
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002510",
"normalized_example_id": "ex_002510",
"source_idx": 2510,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5072,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\varphi(x)=1+\\frac{x^{2}}{2}",
"budget": 5072
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002510",
"normalized_example_id": "ex_002510",
"source_idx": 2510,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5072,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mathrm{~}",
"budget": 841
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002511",
"normalized_example_id": "ex_002511",
"source_idx": 2511,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1402,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mathrm{~}",
"budget": 1122
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002511",
"normalized_example_id": "ex_002511",
"source_idx": 2511,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1402,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mathrm{~}",
"budget": 1402
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002511",
"normalized_example_id": "ex_002511",
"source_idx": 2511,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1402,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{21}{16}",
"budget": 2155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002513",
"normalized_example_id": "ex_002513",
"source_idx": 2513,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{21}{16}",
"budget": 2873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002513",
"normalized_example_id": "ex_002513",
"source_idx": 2513,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{21}{16}",
"budget": 3591
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002513",
"normalized_example_id": "ex_002513",
"source_idx": 2513,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3591,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,\\frac{1}{2},\\frac{1}{3}",
"budget": 2563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002514",
"normalized_example_id": "ex_002514",
"source_idx": 2514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4271,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,\\frac{1}{2},\\frac{1}{3}",
"budget": 3417
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002514",
"normalized_example_id": "ex_002514",
"source_idx": 2514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4271,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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,\\frac{1}{2},\\frac{1}{3}",
"budget": 4271
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002514",
"normalized_example_id": "ex_002514",
"source_idx": 2514,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4271,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\gamma=\\frac{1}{2}(\\alpha+\\beta)",
"budget": 1659
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002516",
"normalized_example_id": "ex_002516",
"source_idx": 2516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2765,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\gamma=\\frac{1}{2}(\\alpha+\\beta)",
"budget": 2212
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002516",
"normalized_example_id": "ex_002516",
"source_idx": 2516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2765,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\gamma=\\frac{1}{2}(\\alpha+\\beta)",
"budget": 2765
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002516",
"normalized_example_id": "ex_002516",
"source_idx": 2516,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2765,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1741
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002517",
"normalized_example_id": "ex_002517",
"source_idx": 2517,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2901,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2321
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002517",
"normalized_example_id": "ex_002517",
"source_idx": 2517,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2901,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2901
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002517",
"normalized_example_id": "ex_002517",
"source_idx": 2517,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2901,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "380",
"budget": 1638
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002520",
"normalized_example_id": "ex_002520",
"source_idx": 2520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2730,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "380",
"budget": 2184
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002520",
"normalized_example_id": "ex_002520",
"source_idx": 2520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2730,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "380",
"budget": 2730
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002520",
"normalized_example_id": "ex_002520",
"source_idx": 2520,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2730,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,3,3),(-4,-4,-4),(1,1,11),(1,11,1),(11,1,1)",
"budget": 2790
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002521",
"normalized_example_id": "ex_002521",
"source_idx": 2521,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4650,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,3,3),(-4,-4,-4),(1,1,11),(1,11,1),(11,1,1)",
"budget": 3720
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002521",
"normalized_example_id": "ex_002521",
"source_idx": 2521,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4650,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,3,3),(-4,-4,-4),(1,1,11),(1,11,1),(11,1,1)",
"budget": 4650
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002521",
"normalized_example_id": "ex_002521",
"source_idx": 2521,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4650,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_1 = x_2 = \\cdots = x_n = 0",
"budget": 2267
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002522",
"normalized_example_id": "ex_002522",
"source_idx": 2522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3778,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_1 = x_2 = \\cdots = x_n = 0",
"budget": 3022
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002522",
"normalized_example_id": "ex_002522",
"source_idx": 2522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3778,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_1 = x_2 = \\cdots = x_n = 0",
"budget": 3778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002522",
"normalized_example_id": "ex_002522",
"source_idx": 2522,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3778,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leq0",
"budget": 1341
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002523",
"normalized_example_id": "ex_002523",
"source_idx": 2523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2235,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leq0",
"budget": 1788
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002523",
"normalized_example_id": "ex_002523",
"source_idx": 2523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2235,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\leq0",
"budget": 2235
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002523",
"normalized_example_id": "ex_002523",
"source_idx": 2523,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2235,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "486",
"budget": 3779
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002525",
"normalized_example_id": "ex_002525",
"source_idx": 2525,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6298,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "486",
"budget": 5038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002525",
"normalized_example_id": "ex_002525",
"source_idx": 2525,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6298,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "486",
"budget": 6298
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002525",
"normalized_example_id": "ex_002525",
"source_idx": 2525,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6298,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\mathrm{C}_{49}^{6}-\\mathrm{C}_{44}^{6}",
"budget": 2358
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002527",
"normalized_example_id": "ex_002527",
"source_idx": 2527,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\mathrm{C}_{49}^{6}-\\mathrm{C}_{44}^{6}",
"budget": 3144
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002527",
"normalized_example_id": "ex_002527",
"source_idx": 2527,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\mathrm{C}_{49}^{6}-\\mathrm{C}_{44}^{6}",
"budget": 3930
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002527",
"normalized_example_id": "ex_002527",
"source_idx": 2527,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 650
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002530",
"normalized_example_id": "ex_002530",
"source_idx": 2530,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1084,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002530",
"normalized_example_id": "ex_002530",
"source_idx": 2530,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1084,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27",
"budget": 1084
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002530",
"normalized_example_id": "ex_002530",
"source_idx": 2530,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1084,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91",
"budget": 1895
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002531",
"normalized_example_id": "ex_002531",
"source_idx": 2531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3158,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91",
"budget": 2526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002531",
"normalized_example_id": "ex_002531",
"source_idx": 2531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3158,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91",
"budget": 3158
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002531",
"normalized_example_id": "ex_002531",
"source_idx": 2531,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3158,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "156",
"budget": 4731
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002532",
"normalized_example_id": "ex_002532",
"source_idx": 2532,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "156",
"budget": 6308
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002532",
"normalized_example_id": "ex_002532",
"source_idx": 2532,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "156",
"budget": 7885
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002532",
"normalized_example_id": "ex_002532",
"source_idx": 2532,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7885,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=105,\\beta=75",
"budget": 2783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002535",
"normalized_example_id": "ex_002535",
"source_idx": 2535,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=105,\\beta=75",
"budget": 3710
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002535",
"normalized_example_id": "ex_002535",
"source_idx": 2535,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\alpha=105,\\beta=75",
"budget": 4638
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002535",
"normalized_example_id": "ex_002535",
"source_idx": 2535,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4638,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = n \\pm \\sqrt{n^2 - m^2}",
"budget": 5314
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002536",
"normalized_example_id": "ex_002536",
"source_idx": 2536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8857,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x = n \\pm \\sqrt{n^2 - m^2}",
"budget": 7086
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002536",
"normalized_example_id": "ex_002536",
"source_idx": 2536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8857,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x = n \\pm \\sqrt{n^2 - m^2}",
"budget": 8857
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002536",
"normalized_example_id": "ex_002536",
"source_idx": 2536,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8857,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{1}{\\sqrt{3}}",
"budget": 4051
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002537",
"normalized_example_id": "ex_002537",
"source_idx": 2537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{1}{\\sqrt{3}}",
"budget": 5402
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002537",
"normalized_example_id": "ex_002537",
"source_idx": 2537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{1}{\\sqrt{3}}",
"budget": 6752
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002537",
"normalized_example_id": "ex_002537",
"source_idx": 2537,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 3132
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002538",
"normalized_example_id": "ex_002538",
"source_idx": 2538,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5220,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 4176
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002538",
"normalized_example_id": "ex_002538",
"source_idx": 2538,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5220,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{7}",
"budget": 5220
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002538",
"normalized_example_id": "ex_002538",
"source_idx": 2538,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5220,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "340",
"budget": 2809
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002539",
"normalized_example_id": "ex_002539",
"source_idx": 2539,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4681,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "340",
"budget": 3745
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002539",
"normalized_example_id": "ex_002539",
"source_idx": 2539,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4681,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "340",
"budget": 4681
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002539",
"normalized_example_id": "ex_002539",
"source_idx": 2539,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4681,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "760",
"budget": 1651
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002540",
"normalized_example_id": "ex_002540",
"source_idx": 2540,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "760",
"budget": 2202
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002540",
"normalized_example_id": "ex_002540",
"source_idx": 2540,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "760",
"budget": 2752
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002540",
"normalized_example_id": "ex_002540",
"source_idx": 2540,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}}{6}",
"budget": 6003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002541",
"normalized_example_id": "ex_002541",
"source_idx": 2541,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}}{6}",
"budget": 8004
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002541",
"normalized_example_id": "ex_002541",
"source_idx": 2541,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{6}}{6}",
"budget": 10005
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002541",
"normalized_example_id": "ex_002541",
"source_idx": 2541,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10005,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(-\\infty, 2-\\frac{a^{3}}{108}\\right]",
"budget": 4450
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002543",
"normalized_example_id": "ex_002543",
"source_idx": 2543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7416,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(-\\infty, 2-\\frac{a^{3}}{108}\\right]",
"budget": 5933
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002543",
"normalized_example_id": "ex_002543",
"source_idx": 2543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7416,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\left(-\\infty, 2-\\frac{a^{3}}{108}\\right]",
"budget": 7416
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002543",
"normalized_example_id": "ex_002543",
"source_idx": 2543,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7416,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5773
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002545",
"normalized_example_id": "ex_002545",
"source_idx": 2545,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9621,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7697
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002545",
"normalized_example_id": "ex_002545",
"source_idx": 2545,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9621,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9621
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002545",
"normalized_example_id": "ex_002545",
"source_idx": 2545,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9621,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 3625
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002548",
"normalized_example_id": "ex_002548",
"source_idx": 2548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6042,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 4834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002548",
"normalized_example_id": "ex_002548",
"source_idx": 2548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6042,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{8}",
"budget": 6042
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002548",
"normalized_example_id": "ex_002548",
"source_idx": 2548,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6042,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n-k+1}^{k}",
"budget": 2287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002550",
"normalized_example_id": "ex_002550",
"source_idx": 2550,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3812,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n-k+1}^{k}",
"budget": 3050
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002550",
"normalized_example_id": "ex_002550",
"source_idx": 2550,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3812,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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_{n-k+1}^{k}",
"budget": 3812
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002550",
"normalized_example_id": "ex_002550",
"source_idx": 2550,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3812,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a=-2",
"budget": 3881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002551",
"normalized_example_id": "ex_002551",
"source_idx": 2551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6468,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a=-2",
"budget": 5174
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002551",
"normalized_example_id": "ex_002551",
"source_idx": 2551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6468,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a=-2",
"budget": 6468
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002551",
"normalized_example_id": "ex_002551",
"source_idx": 2551,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6468,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002553",
"normalized_example_id": "ex_002553",
"source_idx": 2553,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7677,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6142
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002553",
"normalized_example_id": "ex_002553",
"source_idx": 2553,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7677,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7677
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002553",
"normalized_example_id": "ex_002553",
"source_idx": 2553,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7677,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(1,2),B(7,8)",
"budget": 884
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002557",
"normalized_example_id": "ex_002557",
"source_idx": 2557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(1,2),B(7,8)",
"budget": 1179
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002557",
"normalized_example_id": "ex_002557",
"source_idx": 2557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(1,2),B(7,8)",
"budget": 1474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002557",
"normalized_example_id": "ex_002557",
"source_idx": 2557,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1474,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{95}{144}",
"budget": 2647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002558",
"normalized_example_id": "ex_002558",
"source_idx": 2558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{95}{144}",
"budget": 3529
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002558",
"normalized_example_id": "ex_002558",
"source_idx": 2558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{95}{144}",
"budget": 4411
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002558",
"normalized_example_id": "ex_002558",
"source_idx": 2558,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4411,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2865
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002559",
"normalized_example_id": "ex_002559",
"source_idx": 2559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4775,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 3820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002559",
"normalized_example_id": "ex_002559",
"source_idx": 2559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4775,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 4775
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002559",
"normalized_example_id": "ex_002559",
"source_idx": 2559,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4775,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n) = n",
"budget": 4947
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002560",
"normalized_example_id": "ex_002560",
"source_idx": 2560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8245,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n) = n",
"budget": 6596
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002560",
"normalized_example_id": "ex_002560",
"source_idx": 2560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8245,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n) = n",
"budget": 8245
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002560",
"normalized_example_id": "ex_002560",
"source_idx": 2560,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8245,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9.9",
"budget": 5060
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002563",
"normalized_example_id": "ex_002563",
"source_idx": 2563,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9.9",
"budget": 6746
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002563",
"normalized_example_id": "ex_002563",
"source_idx": 2563,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8433,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.