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": "1:1",
"budget": 3360
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005140",
"normalized_example_id": "ex_005140",
"source_idx": 5140,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4200,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1:1",
"budget": 4200
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005140",
"normalized_example_id": "ex_005140",
"source_idx": 5140,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4200,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "131070",
"budget": 4153
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005144",
"normalized_example_id": "ex_005144",
"source_idx": 5144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6921,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "131070",
"budget": 5537
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005144",
"normalized_example_id": "ex_005144",
"source_idx": 5144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6921,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "131070",
"budget": 6921
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005144",
"normalized_example_id": "ex_005144",
"source_idx": 5144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6921,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\bar{x}=74.7,\\sigma=8.5",
"budget": 4843
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005146",
"normalized_example_id": "ex_005146",
"source_idx": 5146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8072,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\bar{x}=74.7,\\sigma=8.5",
"budget": 6458
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005146",
"normalized_example_id": "ex_005146",
"source_idx": 5146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8072,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\bar{x}=74.7,\\sigma=8.5",
"budget": 8072
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005146",
"normalized_example_id": "ex_005146",
"source_idx": 5146,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8072,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4a^{10}",
"budget": 2060
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005153",
"normalized_example_id": "ex_005153",
"source_idx": 5153,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3434,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4a^{10}",
"budget": 2747
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005153",
"normalized_example_id": "ex_005153",
"source_idx": 5153,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3434,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4a^{10}",
"budget": 3434
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005153",
"normalized_example_id": "ex_005153",
"source_idx": 5153,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3434,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1227
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005154",
"normalized_example_id": "ex_005154",
"source_idx": 5154,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2045,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1636
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005154",
"normalized_example_id": "ex_005154",
"source_idx": 5154,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2045,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2045
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005154",
"normalized_example_id": "ex_005154",
"source_idx": 5154,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2045,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{600}{73}",
"budget": 5768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005156",
"normalized_example_id": "ex_005156",
"source_idx": 5156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9613,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{600}{73}",
"budget": 7690
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005156",
"normalized_example_id": "ex_005156",
"source_idx": 5156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9613,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{600}{73}",
"budget": 9613
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005156",
"normalized_example_id": "ex_005156",
"source_idx": 5156,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9613,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12:3:5",
"budget": 2212
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005157",
"normalized_example_id": "ex_005157",
"source_idx": 5157,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12:3:5",
"budget": 2949
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005157",
"normalized_example_id": "ex_005157",
"source_idx": 5157,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12:3:5",
"budget": 3686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005157",
"normalized_example_id": "ex_005157",
"source_idx": 5157,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=\\frac{2}{3}, x_{2}=\\frac{3}{2}",
"budget": 1574
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005163",
"normalized_example_id": "ex_005163",
"source_idx": 5163,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=\\frac{2}{3}, x_{2}=\\frac{3}{2}",
"budget": 2098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005163",
"normalized_example_id": "ex_005163",
"source_idx": 5163,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=\\frac{2}{3}, x_{2}=\\frac{3}{2}",
"budget": 2623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005163",
"normalized_example_id": "ex_005163",
"source_idx": 5163,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 5584
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005164",
"normalized_example_id": "ex_005164",
"source_idx": 5164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9307,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 7446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005164",
"normalized_example_id": "ex_005164",
"source_idx": 5164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9307,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "38",
"budget": 9307
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005164",
"normalized_example_id": "ex_005164",
"source_idx": 5164,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9307,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 2917
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005169",
"normalized_example_id": "ex_005169",
"source_idx": 5169,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4861,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 3889
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005169",
"normalized_example_id": "ex_005169",
"source_idx": 5169,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4861,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30",
"budget": 4861
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005169",
"normalized_example_id": "ex_005169",
"source_idx": 5169,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4861,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5or10",
"budget": 3372
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005170",
"normalized_example_id": "ex_005170",
"source_idx": 5170,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5or10",
"budget": 4496
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005170",
"normalized_example_id": "ex_005170",
"source_idx": 5170,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5or10",
"budget": 5620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005170",
"normalized_example_id": "ex_005170",
"source_idx": 5170,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5620,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mathrm{~}",
"budget": 2016
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005173",
"normalized_example_id": "ex_005173",
"source_idx": 5173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3360,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mathrm{~}",
"budget": 2688
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005173",
"normalized_example_id": "ex_005173",
"source_idx": 5173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3360,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\mathrm{~}",
"budget": 3360
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005173",
"normalized_example_id": "ex_005173",
"source_idx": 5173,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3360,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1727
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005174",
"normalized_example_id": "ex_005174",
"source_idx": 5174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2878,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2302
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005174",
"normalized_example_id": "ex_005174",
"source_idx": 5174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2878,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2878
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005174",
"normalized_example_id": "ex_005174",
"source_idx": 5174,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2878,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.5\\mathrm{~}",
"budget": 5479
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005175",
"normalized_example_id": "ex_005175",
"source_idx": 5175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.5\\mathrm{~}",
"budget": 7305
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005175",
"normalized_example_id": "ex_005175",
"source_idx": 5175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.5\\mathrm{~}",
"budget": 9131
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005175",
"normalized_example_id": "ex_005175",
"source_idx": 5175,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9131,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1091
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005179",
"normalized_example_id": "ex_005179",
"source_idx": 5179,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1818,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005179",
"normalized_example_id": "ex_005179",
"source_idx": 5179,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1818,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1818
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005179",
"normalized_example_id": "ex_005179",
"source_idx": 5179,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1818,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 968
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005180",
"normalized_example_id": "ex_005180",
"source_idx": 5180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1291
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005180",
"normalized_example_id": "ex_005180",
"source_idx": 5180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005180",
"normalized_example_id": "ex_005180",
"source_idx": 5180,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1614,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1456
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005181",
"normalized_example_id": "ex_005181",
"source_idx": 5181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2426,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1941
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005181",
"normalized_example_id": "ex_005181",
"source_idx": 5181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2426,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2426
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005181",
"normalized_example_id": "ex_005181",
"source_idx": 5181,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2426,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.375",
"budget": 1696
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005182",
"normalized_example_id": "ex_005182",
"source_idx": 5182,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2827,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.375",
"budget": 2262
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005182",
"normalized_example_id": "ex_005182",
"source_idx": 5182,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2827,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.375",
"budget": 2827
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005182",
"normalized_example_id": "ex_005182",
"source_idx": 5182,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2827,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{6^{2011}2010!},2010)",
"budget": 3796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005183",
"normalized_example_id": "ex_005183",
"source_idx": 5183,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6326,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{6^{2011}2010!},2010)",
"budget": 5061
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005183",
"normalized_example_id": "ex_005183",
"source_idx": 5183,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6326,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{6^{2011}2010!},2010)",
"budget": 6326
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005183",
"normalized_example_id": "ex_005183",
"source_idx": 5183,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6326,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 4723
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005185",
"normalized_example_id": "ex_005185",
"source_idx": 5185,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7871,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 6297
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005185",
"normalized_example_id": "ex_005185",
"source_idx": 5185,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7871,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 7871
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005185",
"normalized_example_id": "ex_005185",
"source_idx": 5185,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7871,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{1}{2}",
"budget": 1907
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005186",
"normalized_example_id": "ex_005186",
"source_idx": 5186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{1}{2}",
"budget": 2542
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005186",
"normalized_example_id": "ex_005186",
"source_idx": 5186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{1}{2}",
"budget": 3178
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005186",
"normalized_example_id": "ex_005186",
"source_idx": 5186,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3178,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63(\\sqrt{2}-1)\\mathrm{~}^{3}",
"budget": 4439
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005187",
"normalized_example_id": "ex_005187",
"source_idx": 5187,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63(\\sqrt{2}-1)\\mathrm{~}^{3}",
"budget": 5918
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005187",
"normalized_example_id": "ex_005187",
"source_idx": 5187,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "63(\\sqrt{2}-1)\\mathrm{~}^{3}",
"budget": 7398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005187",
"normalized_example_id": "ex_005187",
"source_idx": 5187,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7398,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1172
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005189",
"normalized_example_id": "ex_005189",
"source_idx": 5189,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005189",
"normalized_example_id": "ex_005189",
"source_idx": 5189,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005189",
"normalized_example_id": "ex_005189",
"source_idx": 5189,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1954,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 2429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005191",
"normalized_example_id": "ex_005191",
"source_idx": 5191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4049,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 3239
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005191",
"normalized_example_id": "ex_005191",
"source_idx": 5191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4049,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{3}",
"budget": 4049
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005191",
"normalized_example_id": "ex_005191",
"source_idx": 5191,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4049,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+b+c=0",
"budget": 4449
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005192",
"normalized_example_id": "ex_005192",
"source_idx": 5192,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7415,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+b+c=0",
"budget": 5932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005192",
"normalized_example_id": "ex_005192",
"source_idx": 5192,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7415,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+b+c=0",
"budget": 7415
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005192",
"normalized_example_id": "ex_005192",
"source_idx": 5192,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7415,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1628
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005193",
"normalized_example_id": "ex_005193",
"source_idx": 5193,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2713,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2170
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005193",
"normalized_example_id": "ex_005193",
"source_idx": 5193,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2713,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2713
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005193",
"normalized_example_id": "ex_005193",
"source_idx": 5193,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2713,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 3712
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005194",
"normalized_example_id": "ex_005194",
"source_idx": 5194,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6186,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 4949
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005194",
"normalized_example_id": "ex_005194",
"source_idx": 5194,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6186,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9",
"budget": 6186
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005194",
"normalized_example_id": "ex_005194",
"source_idx": 5194,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6186,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "179.44",
"budget": 2035
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005196",
"normalized_example_id": "ex_005196",
"source_idx": 5196,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "179.44",
"budget": 2713
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005196",
"normalized_example_id": "ex_005196",
"source_idx": 5196,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "179.44",
"budget": 3391
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005196",
"normalized_example_id": "ex_005196",
"source_idx": 5196,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3391,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105",
"budget": 2990
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005197",
"normalized_example_id": "ex_005197",
"source_idx": 5197,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4984,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105",
"budget": 3987
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005197",
"normalized_example_id": "ex_005197",
"source_idx": 5197,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4984,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "105",
"budget": 4984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005197",
"normalized_example_id": "ex_005197",
"source_idx": 5197,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4984,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{11}{2111}\\binom{2111}{100}",
"budget": 3301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005202",
"normalized_example_id": "ex_005202",
"source_idx": 5202,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5501,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{11}{2111}\\binom{2111}{100}",
"budget": 4401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005202",
"normalized_example_id": "ex_005202",
"source_idx": 5202,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5501,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{11}{2111}\\binom{2111}{100}",
"budget": 5501
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005202",
"normalized_example_id": "ex_005202",
"source_idx": 5202,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5501,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 2739
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005203",
"normalized_example_id": "ex_005203",
"source_idx": 5203,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4565,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 3652
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005203",
"normalized_example_id": "ex_005203",
"source_idx": 5203,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4565,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 4565
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005203",
"normalized_example_id": "ex_005203",
"source_idx": 5203,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4565,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln|x-2|-\\frac{3}{(x+2)^{2}}+C",
"budget": 1607
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005204",
"normalized_example_id": "ex_005204",
"source_idx": 5204,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2679,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln|x-2|-\\frac{3}{(x+2)^{2}}+C",
"budget": 2143
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005204",
"normalized_example_id": "ex_005204",
"source_idx": 5204,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2679,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\ln|x-2|-\\frac{3}{(x+2)^{2}}+C",
"budget": 2679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005204",
"normalized_example_id": "ex_005204",
"source_idx": 5204,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2679,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5703
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005205",
"normalized_example_id": "ex_005205",
"source_idx": 5205,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9505,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7604
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005205",
"normalized_example_id": "ex_005205",
"source_idx": 5205,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9505,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9505
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005205",
"normalized_example_id": "ex_005205",
"source_idx": 5205,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9505,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-1,1)",
"budget": 2297
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005208",
"normalized_example_id": "ex_005208",
"source_idx": 5208,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3829,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(-1,1)",
"budget": 3063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_005208",
"normalized_example_id": "ex_005208",
"source_idx": 5208,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3829,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.