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": "145",
"budget": 3526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000956",
"normalized_example_id": "ex_000956",
"source_idx": 956,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5877,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "145",
"budget": 4702
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000956",
"normalized_example_id": "ex_000956",
"source_idx": 956,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5877,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "145",
"budget": 5877
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000956",
"normalized_example_id": "ex_000956",
"source_idx": 956,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5877,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5<V<15",
"budget": 2041
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000957",
"normalized_example_id": "ex_000957",
"source_idx": 957,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3401,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5<V<15",
"budget": 2721
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000957",
"normalized_example_id": "ex_000957",
"source_idx": 957,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3401,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5<V<15",
"budget": 3401
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000957",
"normalized_example_id": "ex_000957",
"source_idx": 957,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3401,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1191
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000960",
"normalized_example_id": "ex_000960",
"source_idx": 960,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1985,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1588
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000960",
"normalized_example_id": "ex_000960",
"source_idx": 960,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1985,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1985
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000960",
"normalized_example_id": "ex_000960",
"source_idx": 960,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1985,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(995,1),(176,10),(80,21)",
"budget": 3047
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000962",
"normalized_example_id": "ex_000962",
"source_idx": 962,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5079,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(995,1),(176,10),(80,21)",
"budget": 4063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000962",
"normalized_example_id": "ex_000962",
"source_idx": 962,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5079,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(995,1),(176,10),(80,21)",
"budget": 5079
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000962",
"normalized_example_id": "ex_000962",
"source_idx": 962,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5079,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1002",
"budget": 2825
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000963",
"normalized_example_id": "ex_000963",
"source_idx": 963,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4708,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1002",
"budget": 3766
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000963",
"normalized_example_id": "ex_000963",
"source_idx": 963,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4708,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1002",
"budget": 4708
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000963",
"normalized_example_id": "ex_000963",
"source_idx": 963,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4708,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20\\sqrt{5}",
"budget": 2709
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000965",
"normalized_example_id": "ex_000965",
"source_idx": 965,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4515,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20\\sqrt{5}",
"budget": 3612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000965",
"normalized_example_id": "ex_000965",
"source_idx": 965,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4515,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20\\sqrt{5}",
"budget": 4515
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000965",
"normalized_example_id": "ex_000965",
"source_idx": 965,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4515,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2021",
"budget": 1643
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000968",
"normalized_example_id": "ex_000968",
"source_idx": 968,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2738,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2021",
"budget": 2190
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000968",
"normalized_example_id": "ex_000968",
"source_idx": 968,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2738,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2021",
"budget": 2738
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000968",
"normalized_example_id": "ex_000968",
"source_idx": 968,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2738,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 6038
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000969",
"normalized_example_id": "ex_000969",
"source_idx": 969,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10064,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 8051
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000969",
"normalized_example_id": "ex_000969",
"source_idx": 969,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10064,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 10064
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000969",
"normalized_example_id": "ex_000969",
"source_idx": 969,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10064,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.18\\mu\\mathrm{}",
"budget": 3924
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000971",
"normalized_example_id": "ex_000971",
"source_idx": 971,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6540,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.18\\mu\\mathrm{}",
"budget": 5232
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000971",
"normalized_example_id": "ex_000971",
"source_idx": 971,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6540,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.18\\mu\\mathrm{}",
"budget": 6540
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000971",
"normalized_example_id": "ex_000971",
"source_idx": 971,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6540,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1628
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000972",
"normalized_example_id": "ex_000972",
"source_idx": 972,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2714,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 2171
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000972",
"normalized_example_id": "ex_000972",
"source_idx": 972,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2714,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 2714
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000972",
"normalized_example_id": "ex_000972",
"source_idx": 972,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2714,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^{2}",
"budget": 1210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000976",
"normalized_example_id": "ex_000976",
"source_idx": 976,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2017,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^{2}",
"budget": 1614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000976",
"normalized_example_id": "ex_000976",
"source_idx": 976,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2017,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "e^{2}",
"budget": 2017
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000976",
"normalized_example_id": "ex_000976",
"source_idx": 976,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2017,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1152
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000978",
"normalized_example_id": "ex_000978",
"source_idx": 978,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1920,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1536
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000978",
"normalized_example_id": "ex_000978",
"source_idx": 978,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1920,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1920
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000978",
"normalized_example_id": "ex_000978",
"source_idx": 978,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1920,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=119\\quad\\text{}\\quadx_{2}=41",
"budget": 2277
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000979",
"normalized_example_id": "ex_000979",
"source_idx": 979,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3795,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=119\\quad\\text{}\\quadx_{2}=41",
"budget": 3036
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000979",
"normalized_example_id": "ex_000979",
"source_idx": 979,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3795,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=119\\quad\\text{}\\quadx_{2}=41",
"budget": 3795
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000979",
"normalized_example_id": "ex_000979",
"source_idx": 979,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3795,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1496
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000981",
"normalized_example_id": "ex_000981",
"source_idx": 981,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2493,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1994
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000981",
"normalized_example_id": "ex_000981",
"source_idx": 981,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2493,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 2493
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000981",
"normalized_example_id": "ex_000981",
"source_idx": 981,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2493,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^2 - 10x - 39 = 0",
"budget": 1538
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000982",
"normalized_example_id": "ex_000982",
"source_idx": 982,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2564,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^2 - 10x - 39 = 0",
"budget": 2051
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000982",
"normalized_example_id": "ex_000982",
"source_idx": 982,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2564,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^2 - 10x - 39 = 0",
"budget": 2564
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000982",
"normalized_example_id": "ex_000982",
"source_idx": 982,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2564,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+C)e^{-x^{2}}",
"budget": 1259
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000983",
"normalized_example_id": "ex_000983",
"source_idx": 983,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2098,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+C)e^{-x^{2}}",
"budget": 1678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000983",
"normalized_example_id": "ex_000983",
"source_idx": 983,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2098,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+C)e^{-x^{2}}",
"budget": 2098
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000983",
"normalized_example_id": "ex_000983",
"source_idx": 983,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2098,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1280
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000984",
"normalized_example_id": "ex_000984",
"source_idx": 984,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2133,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000984",
"normalized_example_id": "ex_000984",
"source_idx": 984,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2133,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000984",
"normalized_example_id": "ex_000984",
"source_idx": 984,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2133,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000987",
"normalized_example_id": "ex_000987",
"source_idx": 987,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1143,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000987",
"normalized_example_id": "ex_000987",
"source_idx": 987,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1143,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 1143
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000987",
"normalized_example_id": "ex_000987",
"source_idx": 987,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1143,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cdot3^{996}",
"budget": 6050
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000988",
"normalized_example_id": "ex_000988",
"source_idx": 988,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10084,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cdot3^{996}",
"budget": 8067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000988",
"normalized_example_id": "ex_000988",
"source_idx": 988,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10084,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\cdot3^{996}",
"budget": 10084
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000988",
"normalized_example_id": "ex_000988",
"source_idx": 988,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10084,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 998
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000990",
"normalized_example_id": "ex_000990",
"source_idx": 990,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1663,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 1330
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000990",
"normalized_example_id": "ex_000990",
"source_idx": 990,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1663,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "24",
"budget": 1663
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000990",
"normalized_example_id": "ex_000990",
"source_idx": 990,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1663,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 3623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000991",
"normalized_example_id": "ex_000991",
"source_idx": 991,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6039,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 4831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000991",
"normalized_example_id": "ex_000991",
"source_idx": 991,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6039,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 6039
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000991",
"normalized_example_id": "ex_000991",
"source_idx": 991,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6039,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 2205
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000993",
"normalized_example_id": "ex_000993",
"source_idx": 993,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3675,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 2940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000993",
"normalized_example_id": "ex_000993",
"source_idx": 993,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3675,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "660",
"budget": 3675
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000993",
"normalized_example_id": "ex_000993",
"source_idx": 993,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3675,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "220",
"budget": 3331
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000994",
"normalized_example_id": "ex_000994",
"source_idx": 994,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5551,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "220",
"budget": 4441
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000994",
"normalized_example_id": "ex_000994",
"source_idx": 994,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5551,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "220",
"budget": 5551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000994",
"normalized_example_id": "ex_000994",
"source_idx": 994,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5551,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{3}",
"budget": 1561
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000995",
"normalized_example_id": "ex_000995",
"source_idx": 995,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2602,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{3}",
"budget": 2082
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000995",
"normalized_example_id": "ex_000995",
"source_idx": 995,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2602,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\sqrt{3}",
"budget": 2602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000995",
"normalized_example_id": "ex_000995",
"source_idx": 995,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2602,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A",
"budget": 928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000999",
"normalized_example_id": "ex_000999",
"source_idx": 999,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1546,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A",
"budget": 1237
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000999",
"normalized_example_id": "ex_000999",
"source_idx": 999,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1546,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "A",
"budget": 1546
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000999",
"normalized_example_id": "ex_000999",
"source_idx": 999,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1546,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+x-2",
"budget": 4154
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001000",
"normalized_example_id": "ex_001000",
"source_idx": 1000,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+x-2",
"budget": 5538
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001000",
"normalized_example_id": "ex_001000",
"source_idx": 1000,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+x-2",
"budget": 6923
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001000",
"normalized_example_id": "ex_001000",
"source_idx": 1000,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6923,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3596
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001002",
"normalized_example_id": "ex_001002",
"source_idx": 1002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5993,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4794
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001002",
"normalized_example_id": "ex_001002",
"source_idx": 1002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5993,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5993
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001002",
"normalized_example_id": "ex_001002",
"source_idx": 1002,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5993,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3775",
"budget": 1448
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001004",
"normalized_example_id": "ex_001004",
"source_idx": 1004,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2414,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3775",
"budget": 1931
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001004",
"normalized_example_id": "ex_001004",
"source_idx": 1004,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2414,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3775",
"budget": 2414
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001004",
"normalized_example_id": "ex_001004",
"source_idx": 1004,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2414,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52\\mathrm{~}",
"budget": 1951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001005",
"normalized_example_id": "ex_001005",
"source_idx": 1005,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3252,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52\\mathrm{~}",
"budget": 2602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001005",
"normalized_example_id": "ex_001005",
"source_idx": 1005,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3252,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "52\\mathrm{~}",
"budget": 3252
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001005",
"normalized_example_id": "ex_001005",
"source_idx": 1005,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3252,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "59",
"budget": 3564
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001007",
"normalized_example_id": "ex_001007",
"source_idx": 1007,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5940,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "59",
"budget": 4752
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001007",
"normalized_example_id": "ex_001007",
"source_idx": 1007,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5940,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "59",
"budget": 5940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001007",
"normalized_example_id": "ex_001007",
"source_idx": 1007,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5940,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{14}{3}\\sqrt{7}",
"budget": 5361
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001011",
"normalized_example_id": "ex_001011",
"source_idx": 1011,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8935,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{14}{3}\\sqrt{7}",
"budget": 7148
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001011",
"normalized_example_id": "ex_001011",
"source_idx": 1011,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8935,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{14}{3}\\sqrt{7}",
"budget": 8935
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001011",
"normalized_example_id": "ex_001011",
"source_idx": 1011,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8935,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30,60",
"budget": 2807
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001016",
"normalized_example_id": "ex_001016",
"source_idx": 1016,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4679,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30,60",
"budget": 3743
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001016",
"normalized_example_id": "ex_001016",
"source_idx": 1016,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4679,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "30,60",
"budget": 4679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001016",
"normalized_example_id": "ex_001016",
"source_idx": 1016,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4679,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32\\sqrt{3}+48\\mathrm{~}^{2}",
"budget": 1507
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001017",
"normalized_example_id": "ex_001017",
"source_idx": 1017,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2512,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32\\sqrt{3}+48\\mathrm{~}^{2}",
"budget": 2010
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001017",
"normalized_example_id": "ex_001017",
"source_idx": 1017,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2512,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32\\sqrt{3}+48\\mathrm{~}^{2}",
"budget": 2512
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001017",
"normalized_example_id": "ex_001017",
"source_idx": 1017,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2512,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "208",
"budget": 1972
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001019",
"normalized_example_id": "ex_001019",
"source_idx": 1019,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3286,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.