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": "-1,1,2",
"budget": 4589
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001335",
"normalized_example_id": "ex_001335",
"source_idx": 1335,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7649,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1,1,2",
"budget": 6119
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001335",
"normalized_example_id": "ex_001335",
"source_idx": 1335,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7649,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1,1,2",
"budget": 7649
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001335",
"normalized_example_id": "ex_001335",
"source_idx": 1335,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7649,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{-x^{3}+x^{2}+1}{2 x(1-x)}",
"budget": 2371
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001336",
"normalized_example_id": "ex_001336",
"source_idx": 1336,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3951,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{-x^{3}+x^{2}+1}{2 x(1-x)}",
"budget": 3161
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001336",
"normalized_example_id": "ex_001336",
"source_idx": 1336,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3951,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{-x^{3}+x^{2}+1}{2 x(1-x)}",
"budget": 3951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001336",
"normalized_example_id": "ex_001336",
"source_idx": 1336,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3951,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,4),(4,1),(5,5)",
"budget": 3613
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001340",
"normalized_example_id": "ex_001340",
"source_idx": 1340,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,4),(4,1),(5,5)",
"budget": 4818
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001340",
"normalized_example_id": "ex_001340",
"source_idx": 1340,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,4),(4,1),(5,5)",
"budget": 6022
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001340",
"normalized_example_id": "ex_001340",
"source_idx": 1340,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001343",
"normalized_example_id": "ex_001343",
"source_idx": 1343,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1821,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001343",
"normalized_example_id": "ex_001343",
"source_idx": 1343,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1821,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001343",
"normalized_example_id": "ex_001343",
"source_idx": 1343,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1821,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3484
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001344",
"normalized_example_id": "ex_001344",
"source_idx": 1344,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4645
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001344",
"normalized_example_id": "ex_001344",
"source_idx": 1344,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001344",
"normalized_example_id": "ex_001344",
"source_idx": 1344,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0-4)^2<15.917",
"budget": 4981
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001345",
"normalized_example_id": "ex_001345",
"source_idx": 1345,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8301,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0-4)^2<15.917",
"budget": 6641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001345",
"normalized_example_id": "ex_001345",
"source_idx": 1345,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8301,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(0-4)^2<15.917",
"budget": 8301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001345",
"normalized_example_id": "ex_001345",
"source_idx": 1345,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8301,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6087
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001346",
"normalized_example_id": "ex_001346",
"source_idx": 1346,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10145,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8116
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001346",
"normalized_example_id": "ex_001346",
"source_idx": 1346,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10145,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 10145
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001346",
"normalized_example_id": "ex_001346",
"source_idx": 1346,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 10145,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4223
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001347",
"normalized_example_id": "ex_001347",
"source_idx": 1347,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7039,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5631
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001347",
"normalized_example_id": "ex_001347",
"source_idx": 1347,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7039,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7039
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001347",
"normalized_example_id": "ex_001347",
"source_idx": 1347,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7039,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "448",
"budget": 3019
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001349",
"normalized_example_id": "ex_001349",
"source_idx": 1349,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5031,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "448",
"budget": 4025
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001349",
"normalized_example_id": "ex_001349",
"source_idx": 1349,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5031,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "448",
"budget": 5031
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001349",
"normalized_example_id": "ex_001349",
"source_idx": 1349,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5031,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\circ}",
"budget": 4375
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001351",
"normalized_example_id": "ex_001351",
"source_idx": 1351,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7291,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\circ}",
"budget": 5833
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001351",
"normalized_example_id": "ex_001351",
"source_idx": 1351,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7291,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{\\circ}",
"budget": 7291
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001351",
"normalized_example_id": "ex_001351",
"source_idx": 1351,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7291,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n)=n+k",
"budget": 2834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001352",
"normalized_example_id": "ex_001352",
"source_idx": 1352,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4723,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n)=n+k",
"budget": 3778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001352",
"normalized_example_id": "ex_001352",
"source_idx": 1352,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4723,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(n)=n+k",
"budget": 4723
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001352",
"normalized_example_id": "ex_001352",
"source_idx": 1352,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4723,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{1}{2}",
"budget": 4429
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001353",
"normalized_example_id": "ex_001353",
"source_idx": 1353,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7381,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{1}{2}",
"budget": 5905
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001353",
"normalized_example_id": "ex_001353",
"source_idx": 1353,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7381,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=\\frac{1}{2}",
"budget": 7381
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001353",
"normalized_example_id": "ex_001353",
"source_idx": 1353,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7381,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "89",
"budget": 4270
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001354",
"normalized_example_id": "ex_001354",
"source_idx": 1354,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7117,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "89",
"budget": 5694
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001354",
"normalized_example_id": "ex_001354",
"source_idx": 1354,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7117,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "89",
"budget": 7117
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001354",
"normalized_example_id": "ex_001354",
"source_idx": 1354,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7117,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;2;3)",
"budget": 5536
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001356",
"normalized_example_id": "ex_001356",
"source_idx": 1356,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;2;3)",
"budget": 7382
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001356",
"normalized_example_id": "ex_001356",
"source_idx": 1356,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;2;3)",
"budget": 9227
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001356",
"normalized_example_id": "ex_001356",
"source_idx": 1356,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9227,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "121",
"budget": 2365
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001357",
"normalized_example_id": "ex_001357",
"source_idx": 1357,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "121",
"budget": 3154
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001357",
"normalized_example_id": "ex_001357",
"source_idx": 1357,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "121",
"budget": 3942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001357",
"normalized_example_id": "ex_001357",
"source_idx": 1357,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 3284
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001358",
"normalized_example_id": "ex_001358",
"source_idx": 1358,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 4378
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001358",
"normalized_example_id": "ex_001358",
"source_idx": 1358,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 5473
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001358",
"normalized_example_id": "ex_001358",
"source_idx": 1358,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5473,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14080",
"budget": 4259
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001362",
"normalized_example_id": "ex_001362",
"source_idx": 1362,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14080",
"budget": 5679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001362",
"normalized_example_id": "ex_001362",
"source_idx": 1362,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14080",
"budget": 7099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001362",
"normalized_example_id": "ex_001362",
"source_idx": 1362,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7099,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1097
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001364",
"normalized_example_id": "ex_001364",
"source_idx": 1364,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1829,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1463
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001364",
"normalized_example_id": "ex_001364",
"source_idx": 1364,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1829,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1829
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001364",
"normalized_example_id": "ex_001364",
"source_idx": 1364,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1829,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4015440",
"budget": 1406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001366",
"normalized_example_id": "ex_001366",
"source_idx": 1366,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2344,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4015440",
"budget": 1875
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001366",
"normalized_example_id": "ex_001366",
"source_idx": 1366,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2344,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4015440",
"budget": 2344
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001366",
"normalized_example_id": "ex_001366",
"source_idx": 1366,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2344,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 868
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001368",
"normalized_example_id": "ex_001368",
"source_idx": 1368,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1446,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1157
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001368",
"normalized_example_id": "ex_001368",
"source_idx": 1368,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1446,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1446
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001368",
"normalized_example_id": "ex_001368",
"source_idx": 1368,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1446,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{2}+\\sqrt{3}",
"budget": 1765
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001369",
"normalized_example_id": "ex_001369",
"source_idx": 1369,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{2}+\\sqrt{3}",
"budget": 2354
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001369",
"normalized_example_id": "ex_001369",
"source_idx": 1369,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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+\\sqrt{2}+\\sqrt{3}",
"budget": 2942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001369",
"normalized_example_id": "ex_001369",
"source_idx": 1369,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2942,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64,108,288,864,1728,10368",
"budget": 2917
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001372",
"normalized_example_id": "ex_001372",
"source_idx": 1372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4862,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64,108,288,864,1728,10368",
"budget": 3890
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001372",
"normalized_example_id": "ex_001372",
"source_idx": 1372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4862,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "64,108,288,864,1728,10368",
"budget": 4862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001372",
"normalized_example_id": "ex_001372",
"source_idx": 1372,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4862,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "102",
"budget": 4127
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001375",
"normalized_example_id": "ex_001375",
"source_idx": 1375,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6878,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "102",
"budget": 5502
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001375",
"normalized_example_id": "ex_001375",
"source_idx": 1375,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6878,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "102",
"budget": 6878
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001375",
"normalized_example_id": "ex_001375",
"source_idx": 1375,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6878,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 3161
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001376",
"normalized_example_id": "ex_001376",
"source_idx": 1376,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5269,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 4215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001376",
"normalized_example_id": "ex_001376",
"source_idx": 1376,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5269,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 5269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001376",
"normalized_example_id": "ex_001376",
"source_idx": 1376,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5269,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27633",
"budget": 3626
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001377",
"normalized_example_id": "ex_001377",
"source_idx": 1377,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27633",
"budget": 4835
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001377",
"normalized_example_id": "ex_001377",
"source_idx": 1377,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27633",
"budget": 6044
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001377",
"normalized_example_id": "ex_001377",
"source_idx": 1377,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6044,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 4814
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001378",
"normalized_example_id": "ex_001378",
"source_idx": 1378,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8023,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 6418
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001378",
"normalized_example_id": "ex_001378",
"source_idx": 1378,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8023,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 8023
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001378",
"normalized_example_id": "ex_001378",
"source_idx": 1378,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8023,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{27}",
"budget": 4168
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001381",
"normalized_example_id": "ex_001381",
"source_idx": 1381,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{27}",
"budget": 5557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001381",
"normalized_example_id": "ex_001381",
"source_idx": 1381,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{10}{27}",
"budget": 6946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001381",
"normalized_example_id": "ex_001381",
"source_idx": 1381,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\frac{14}{41}",
"budget": 3290
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001382",
"normalized_example_id": "ex_001382",
"source_idx": 1382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\frac{14}{41}",
"budget": 4387
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001382",
"normalized_example_id": "ex_001382",
"source_idx": 1382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 \\frac{14}{41}",
"budget": 5484
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001382",
"normalized_example_id": "ex_001382",
"source_idx": 1382,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9802",
"budget": 3461
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001383",
"normalized_example_id": "ex_001383",
"source_idx": 1383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5768,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9802",
"budget": 4614
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001383",
"normalized_example_id": "ex_001383",
"source_idx": 1383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5768,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9802",
"budget": 5768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001383",
"normalized_example_id": "ex_001383",
"source_idx": 1383,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5768,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 627
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001384",
"normalized_example_id": "ex_001384",
"source_idx": 1384,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1045,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 836
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001384",
"normalized_example_id": "ex_001384",
"source_idx": 1384,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1045,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13",
"budget": 1045
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001384",
"normalized_example_id": "ex_001384",
"source_idx": 1384,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1045,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{8}",
"budget": 4105
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001387",
"normalized_example_id": "ex_001387",
"source_idx": 1387,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6841,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{8}",
"budget": 5473
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001387",
"normalized_example_id": "ex_001387",
"source_idx": 1387,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6841,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{8}",
"budget": 6841
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001387",
"normalized_example_id": "ex_001387",
"source_idx": 1387,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6841,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 4277
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001388",
"normalized_example_id": "ex_001388",
"source_idx": 1388,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7128,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 5702
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001388",
"normalized_example_id": "ex_001388",
"source_idx": 1388,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7128,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "C",
"budget": 7128
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001388",
"normalized_example_id": "ex_001388",
"source_idx": 1388,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7128,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2009
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001389",
"normalized_example_id": "ex_001389",
"source_idx": 1389,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3348,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2678
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001389",
"normalized_example_id": "ex_001389",
"source_idx": 1389,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3348,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3348
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001389",
"normalized_example_id": "ex_001389",
"source_idx": 1389,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3348,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1606
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001390",
"normalized_example_id": "ex_001390",
"source_idx": 1390,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2676,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.