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": "\\sqrt{7}",
"budget": 1914
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003712",
"normalized_example_id": "ex_003712",
"source_idx": 3712,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2392,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{7}",
"budget": 2392
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003712",
"normalized_example_id": "ex_003712",
"source_idx": 3712,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2392,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3475
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003713",
"normalized_example_id": "ex_003713",
"source_idx": 3713,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5791,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4633
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003713",
"normalized_example_id": "ex_003713",
"source_idx": 3713,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5791,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5791
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003713",
"normalized_example_id": "ex_003713",
"source_idx": 3713,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5791,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 2612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003714",
"normalized_example_id": "ex_003714",
"source_idx": 3714,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4353,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 3482
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003714",
"normalized_example_id": "ex_003714",
"source_idx": 3714,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4353,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "23",
"budget": 4353
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003714",
"normalized_example_id": "ex_003714",
"source_idx": 3714,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4353,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003716",
"normalized_example_id": "ex_003716",
"source_idx": 3716,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1062
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003716",
"normalized_example_id": "ex_003716",
"source_idx": 3716,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1327
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003716",
"normalized_example_id": "ex_003716",
"source_idx": 3716,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1327,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13.5",
"budget": 1263
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003718",
"normalized_example_id": "ex_003718",
"source_idx": 3718,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2105,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13.5",
"budget": 1684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003718",
"normalized_example_id": "ex_003718",
"source_idx": 3718,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2105,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "13.5",
"budget": 2105
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003718",
"normalized_example_id": "ex_003718",
"source_idx": 3718,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2105,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{p^2}{4}",
"budget": 5116
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003719",
"normalized_example_id": "ex_003719",
"source_idx": 3719,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8526,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{p^2}{4}",
"budget": 6821
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003719",
"normalized_example_id": "ex_003719",
"source_idx": 3719,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8526,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{p^2}{4}",
"budget": 8526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003719",
"normalized_example_id": "ex_003719",
"source_idx": 3719,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8526,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1168
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003720",
"normalized_example_id": "ex_003720",
"source_idx": 3720,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1557
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003720",
"normalized_example_id": "ex_003720",
"source_idx": 3720,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003720",
"normalized_example_id": "ex_003720",
"source_idx": 3720,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(n+2)^2 - 2 \\left\\lfloor \\frac{n}{2} \\right\\rfloor}{4}",
"budget": 5032
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003721",
"normalized_example_id": "ex_003721",
"source_idx": 3721,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8387,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(n+2)^2 - 2 \\left\\lfloor \\frac{n}{2} \\right\\rfloor}{4}",
"budget": 6710
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003721",
"normalized_example_id": "ex_003721",
"source_idx": 3721,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8387,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(n+2)^2 - 2 \\left\\lfloor \\frac{n}{2} \\right\\rfloor}{4}",
"budget": 8387
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003721",
"normalized_example_id": "ex_003721",
"source_idx": 3721,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8387,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{11}|7b-4a|",
"budget": 4445
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003722",
"normalized_example_id": "ex_003722",
"source_idx": 3722,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{11}|7b-4a|",
"budget": 5926
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003722",
"normalized_example_id": "ex_003722",
"source_idx": 3722,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{11}|7b-4a|",
"budget": 7408
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003722",
"normalized_example_id": "ex_003722",
"source_idx": 3722,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7408,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 2811
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003723",
"normalized_example_id": "ex_003723",
"source_idx": 3723,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4685,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 3748
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003723",
"normalized_example_id": "ex_003723",
"source_idx": 3723,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4685,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "33",
"budget": 4685
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003723",
"normalized_example_id": "ex_003723",
"source_idx": 3723,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4685,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "d_{2}<d_{1}<1",
"budget": 1736
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003725",
"normalized_example_id": "ex_003725",
"source_idx": 3725,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2894,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "d_{2}<d_{1}<1",
"budget": 2315
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003725",
"normalized_example_id": "ex_003725",
"source_idx": 3725,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2894,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "d_{2}<d_{1}<1",
"budget": 2894
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003725",
"normalized_example_id": "ex_003725",
"source_idx": 3725,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2894,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2992
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003726",
"normalized_example_id": "ex_003726",
"source_idx": 3726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4986,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003726",
"normalized_example_id": "ex_003726",
"source_idx": 3726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4986,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4986
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003726",
"normalized_example_id": "ex_003726",
"source_idx": 3726,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4986,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x,y)=(\\frac{\\pi}{2},\\frac{\\pi}{2})",
"budget": 2419
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003727",
"normalized_example_id": "ex_003727",
"source_idx": 3727,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4032,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x,y)=(\\frac{\\pi}{2},\\frac{\\pi}{2})",
"budget": 3226
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003727",
"normalized_example_id": "ex_003727",
"source_idx": 3727,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4032,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(x,y)=(\\frac{\\pi}{2},\\frac{\\pi}{2})",
"budget": 4032
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003727",
"normalized_example_id": "ex_003727",
"source_idx": 3727,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4032,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,0,3,1),(-1,0,-3,-1),(3,1,1,0),(-3,-1,-1,0)",
"budget": 5455
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003729",
"normalized_example_id": "ex_003729",
"source_idx": 3729,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,0,3,1),(-1,0,-3,-1),(3,1,1,0),(-3,-1,-1,0)",
"budget": 7274
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003729",
"normalized_example_id": "ex_003729",
"source_idx": 3729,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(1,0,3,1),(-1,0,-3,-1),(3,1,1,0),(-3,-1,-1,0)",
"budget": 9092
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003729",
"normalized_example_id": "ex_003729",
"source_idx": 3729,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9092,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5x^{4}}{\\cos^{2}x^{5}}",
"budget": 1348
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003730",
"normalized_example_id": "ex_003730",
"source_idx": 3730,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2247,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5x^{4}}{\\cos^{2}x^{5}}",
"budget": 1798
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003730",
"normalized_example_id": "ex_003730",
"source_idx": 3730,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2247,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5x^{4}}{\\cos^{2}x^{5}}",
"budget": 2247
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003730",
"normalized_example_id": "ex_003730",
"source_idx": 3730,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2247,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-2020",
"budget": 5029
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003732",
"normalized_example_id": "ex_003732",
"source_idx": 3732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8382,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-2020",
"budget": 6706
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003732",
"normalized_example_id": "ex_003732",
"source_idx": 3732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8382,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-2020",
"budget": 8382
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003732",
"normalized_example_id": "ex_003732",
"source_idx": 3732,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8382,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;-2)\\cup(-2;1)\\cup(1;2)",
"budget": 4768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003735",
"normalized_example_id": "ex_003735",
"source_idx": 3735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7947,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;-2)\\cup(-2;1)\\cup(1;2)",
"budget": 6358
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003735",
"normalized_example_id": "ex_003735",
"source_idx": 3735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7947,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;-2)\\cup(-2;1)\\cup(1;2)",
"budget": 7947
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003735",
"normalized_example_id": "ex_003735",
"source_idx": 3735,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7947,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2007",
"budget": 1355
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003736",
"normalized_example_id": "ex_003736",
"source_idx": 3736,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2258,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2007",
"budget": 1806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003736",
"normalized_example_id": "ex_003736",
"source_idx": 3736,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2258,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2007",
"budget": 2258
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003736",
"normalized_example_id": "ex_003736",
"source_idx": 3736,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2258,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(n+1)!",
"budget": 2465
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003740",
"normalized_example_id": "ex_003740",
"source_idx": 3740,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(n+1)!",
"budget": 3287
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003740",
"normalized_example_id": "ex_003740",
"source_idx": 3740,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(n+1)!",
"budget": 4109
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003740",
"normalized_example_id": "ex_003740",
"source_idx": 3740,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{11}{9}",
"budget": 3262
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003742",
"normalized_example_id": "ex_003742",
"source_idx": 3742,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{11}{9}",
"budget": 4349
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003742",
"normalized_example_id": "ex_003742",
"source_idx": 3742,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{11}{9}",
"budget": 5436
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003742",
"normalized_example_id": "ex_003742",
"source_idx": 3742,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5436,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{-\\frac{1}{\\pi}}",
"budget": 2205
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003743",
"normalized_example_id": "ex_003743",
"source_idx": 3743,
"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": "e^{-\\frac{1}{\\pi}}",
"budget": 2940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003743",
"normalized_example_id": "ex_003743",
"source_idx": 3743,
"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": "e^{-\\frac{1}{\\pi}}",
"budget": 3675
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003743",
"normalized_example_id": "ex_003743",
"source_idx": 3743,
"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": "19:30",
"budget": 1425
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003744",
"normalized_example_id": "ex_003744",
"source_idx": 3744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2375,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19:30",
"budget": 1900
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003744",
"normalized_example_id": "ex_003744",
"source_idx": 3744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2375,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19:30",
"budget": 2375
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003744",
"normalized_example_id": "ex_003744",
"source_idx": 3744,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2375,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4757
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003745",
"normalized_example_id": "ex_003745",
"source_idx": 3745,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7928,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6342
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003745",
"normalized_example_id": "ex_003745",
"source_idx": 3745,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7928,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003745",
"normalized_example_id": "ex_003745",
"source_idx": 3745,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7928,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 839
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003746",
"normalized_example_id": "ex_003746",
"source_idx": 3746,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1399,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1119
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003746",
"normalized_example_id": "ex_003746",
"source_idx": 3746,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1399,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1399
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003746",
"normalized_example_id": "ex_003746",
"source_idx": 3746,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1399,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "379,397,739,937",
"budget": 2699
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003747",
"normalized_example_id": "ex_003747",
"source_idx": 3747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4499,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "379,397,739,937",
"budget": 3599
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003747",
"normalized_example_id": "ex_003747",
"source_idx": 3747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4499,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "379,397,739,937",
"budget": 4499
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003747",
"normalized_example_id": "ex_003747",
"source_idx": 3747,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4499,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 5398
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003748",
"normalized_example_id": "ex_003748",
"source_idx": 3748,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8996,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 7197
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003748",
"normalized_example_id": "ex_003748",
"source_idx": 3748,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8996,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2",
"budget": 8996
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003748",
"normalized_example_id": "ex_003748",
"source_idx": 3748,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8996,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\ln2",
"budget": 2993
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003750",
"normalized_example_id": "ex_003750",
"source_idx": 3750,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4989,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\ln2",
"budget": 3991
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003750",
"normalized_example_id": "ex_003750",
"source_idx": 3750,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4989,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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\\ln2",
"budget": 4989
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003750",
"normalized_example_id": "ex_003750",
"source_idx": 3750,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4989,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2015}",
"budget": 2316
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003754",
"normalized_example_id": "ex_003754",
"source_idx": 3754,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3860,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2015}",
"budget": 3088
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003754",
"normalized_example_id": "ex_003754",
"source_idx": 3754,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3860,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{2015}",
"budget": 3860
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003754",
"normalized_example_id": "ex_003754",
"source_idx": 3754,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3860,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15\\pi^{4}}{2^{10}}-\\frac{\\pi}{4}",
"budget": 1313
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003757",
"normalized_example_id": "ex_003757",
"source_idx": 3757,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2188,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15\\pi^{4}}{2^{10}}-\\frac{\\pi}{4}",
"budget": 1750
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003757",
"normalized_example_id": "ex_003757",
"source_idx": 3757,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2188,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{15\\pi^{4}}{2^{10}}-\\frac{\\pi}{4}",
"budget": 2188
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003757",
"normalized_example_id": "ex_003757",
"source_idx": 3757,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2188,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{658} \\times 2",
"budget": 1699
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003766",
"normalized_example_id": "ex_003766",
"source_idx": 3766,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{658} \\times 2",
"budget": 2265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003766",
"normalized_example_id": "ex_003766",
"source_idx": 3766,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{658} \\times 2",
"budget": 2831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003766",
"normalized_example_id": "ex_003766",
"source_idx": 3766,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2831,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003767",
"normalized_example_id": "ex_003767",
"source_idx": 3767,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6343,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5074
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003767",
"normalized_example_id": "ex_003767",
"source_idx": 3767,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6343,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6343
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003767",
"normalized_example_id": "ex_003767",
"source_idx": 3767,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6343,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 x^{2}+4 x+24",
"budget": 1265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003769",
"normalized_example_id": "ex_003769",
"source_idx": 3769,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 x^{2}+4 x+24",
"budget": 1687
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003769",
"normalized_example_id": "ex_003769",
"source_idx": 3769,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 x^{2}+4 x+24",
"budget": 2109
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003769",
"normalized_example_id": "ex_003769",
"source_idx": 3769,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2109,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}-2",
"budget": 2873
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003770",
"normalized_example_id": "ex_003770",
"source_idx": 3770,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4789,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}-2",
"budget": 3831
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003770",
"normalized_example_id": "ex_003770",
"source_idx": 3770,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4789,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{3}-2",
"budget": 4789
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003770",
"normalized_example_id": "ex_003770",
"source_idx": 3770,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4789,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900",
"budget": 645
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003772",
"normalized_example_id": "ex_003772",
"source_idx": 3772,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "900",
"budget": 860
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_003772",
"normalized_example_id": "ex_003772",
"source_idx": 3772,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1075,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.