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": "-\\frac{1}{4}\\cdot(\\arccosx)^{4}+\\arccosx+C",
"budget": 1530
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001081",
"normalized_example_id": "ex_001081",
"source_idx": 1081,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1530,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 4881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001083",
"normalized_example_id": "ex_001083",
"source_idx": 1083,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 6508
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001083",
"normalized_example_id": "ex_001083",
"source_idx": 1083,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 8135
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001083",
"normalized_example_id": "ex_001083",
"source_idx": 1083,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8135,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 2747
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001084",
"normalized_example_id": "ex_001084",
"source_idx": 1084,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4579,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 3663
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001084",
"normalized_example_id": "ex_001084",
"source_idx": 1084,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4579,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 4579
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001084",
"normalized_example_id": "ex_001084",
"source_idx": 1084,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4579,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 5390
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001088",
"normalized_example_id": "ex_001088",
"source_idx": 1088,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8983,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 7186
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001088",
"normalized_example_id": "ex_001088",
"source_idx": 1088,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8983,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "100",
"budget": 8983
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001088",
"normalized_example_id": "ex_001088",
"source_idx": 1088,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8983,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2007}",
"budget": 3406
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001089",
"normalized_example_id": "ex_001089",
"source_idx": 1089,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5676,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2007}",
"budget": 4541
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001089",
"normalized_example_id": "ex_001089",
"source_idx": 1089,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5676,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2007}",
"budget": 5676
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001089",
"normalized_example_id": "ex_001089",
"source_idx": 1089,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5676,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8}{3}",
"budget": 3624
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001090",
"normalized_example_id": "ex_001090",
"source_idx": 1090,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6040,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8}{3}",
"budget": 4832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001090",
"normalized_example_id": "ex_001090",
"source_idx": 1090,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6040,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{8}{3}",
"budget": 6040
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001090",
"normalized_example_id": "ex_001090",
"source_idx": 1090,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6040,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "239297520",
"budget": 2746
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001092",
"normalized_example_id": "ex_001092",
"source_idx": 1092,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4576,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "239297520",
"budget": 3661
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001092",
"normalized_example_id": "ex_001092",
"source_idx": 1092,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4576,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "239297520",
"budget": 4576
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001092",
"normalized_example_id": "ex_001092",
"source_idx": 1092,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4576,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.24",
"budget": 2590
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001093",
"normalized_example_id": "ex_001093",
"source_idx": 1093,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.24",
"budget": 3454
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001093",
"normalized_example_id": "ex_001093",
"source_idx": 1093,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.24",
"budget": 4317
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001093",
"normalized_example_id": "ex_001093",
"source_idx": 1093,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4317,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4082
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001094",
"normalized_example_id": "ex_001094",
"source_idx": 1094,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6803,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5442
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001094",
"normalized_example_id": "ex_001094",
"source_idx": 1094,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6803,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6803
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001094",
"normalized_example_id": "ex_001094",
"source_idx": 1094,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6803,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001100",
"normalized_example_id": "ex_001100",
"source_idx": 1100,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6585,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5268
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001100",
"normalized_example_id": "ex_001100",
"source_idx": 1100,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6585,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6585
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001100",
"normalized_example_id": "ex_001100",
"source_idx": 1100,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6585,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 2138
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001102",
"normalized_example_id": "ex_001102",
"source_idx": 1102,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3563,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 2850
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001102",
"normalized_example_id": "ex_001102",
"source_idx": 1102,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3563,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "36",
"budget": 3563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001102",
"normalized_example_id": "ex_001102",
"source_idx": 1102,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3563,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 2413
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001103",
"normalized_example_id": "ex_001103",
"source_idx": 1103,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 3218
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001103",
"normalized_example_id": "ex_001103",
"source_idx": 1103,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "20",
"budget": 4022
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001103",
"normalized_example_id": "ex_001103",
"source_idx": 1103,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4022,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1318",
"budget": 3738
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001105",
"normalized_example_id": "ex_001105",
"source_idx": 1105,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6230,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1318",
"budget": 4984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001105",
"normalized_example_id": "ex_001105",
"source_idx": 1105,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6230,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1318",
"budget": 6230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001105",
"normalized_example_id": "ex_001105",
"source_idx": 1105,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6230,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.54",
"budget": 3793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001106",
"normalized_example_id": "ex_001106",
"source_idx": 1106,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.54",
"budget": 5057
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001106",
"normalized_example_id": "ex_001106",
"source_idx": 1106,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.54",
"budget": 6321
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001106",
"normalized_example_id": "ex_001106",
"source_idx": 1106,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6321,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 4768
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001109",
"normalized_example_id": "ex_001109",
"source_idx": 1109,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 6357
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001109",
"normalized_example_id": "ex_001109",
"source_idx": 1109,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 7946
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001109",
"normalized_example_id": "ex_001109",
"source_idx": 1109,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7946,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50\\mathrm{}/\\mathrm{}",
"budget": 1357
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001111",
"normalized_example_id": "ex_001111",
"source_idx": 1111,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2261,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50\\mathrm{}/\\mathrm{}",
"budget": 1809
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001111",
"normalized_example_id": "ex_001111",
"source_idx": 1111,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2261,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50\\mathrm{}/\\mathrm{}",
"budget": 2261
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001111",
"normalized_example_id": "ex_001111",
"source_idx": 1111,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2261,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(4a+b)b\\sqrt{3}}{8}",
"budget": 2388
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001112",
"normalized_example_id": "ex_001112",
"source_idx": 1112,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3980,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(4a+b)b\\sqrt{3}}{8}",
"budget": 3184
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001112",
"normalized_example_id": "ex_001112",
"source_idx": 1112,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3980,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{(4a+b)b\\sqrt{3}}{8}",
"budget": 3980
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001112",
"normalized_example_id": "ex_001112",
"source_idx": 1112,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3980,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 778
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001114",
"normalized_example_id": "ex_001114",
"source_idx": 1114,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1296,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1037
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001114",
"normalized_example_id": "ex_001114",
"source_idx": 1114,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1296,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1296
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001114",
"normalized_example_id": "ex_001114",
"source_idx": 1114,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1296,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-0.5",
"budget": 3103
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001115",
"normalized_example_id": "ex_001115",
"source_idx": 1115,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5171,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-0.5",
"budget": 4137
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001115",
"normalized_example_id": "ex_001115",
"source_idx": 1115,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5171,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-0.5",
"budget": 5171
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001115",
"normalized_example_id": "ex_001115",
"source_idx": 1115,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5171,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "189",
"budget": 994
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001116",
"normalized_example_id": "ex_001116",
"source_idx": 1116,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "189",
"budget": 1326
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001116",
"normalized_example_id": "ex_001116",
"source_idx": 1116,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "189",
"budget": 1657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001116",
"normalized_example_id": "ex_001116",
"source_idx": 1116,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4880
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001117",
"normalized_example_id": "ex_001117",
"source_idx": 1117,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8133,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6506
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001117",
"normalized_example_id": "ex_001117",
"source_idx": 1117,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8133,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 8133
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001117",
"normalized_example_id": "ex_001117",
"source_idx": 1117,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8133,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "raspberry",
"budget": 1187
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001121",
"normalized_example_id": "ex_001121",
"source_idx": 1121,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1978,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "raspberry",
"budget": 1582
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001121",
"normalized_example_id": "ex_001121",
"source_idx": 1121,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1978,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "raspberry",
"budget": 1978
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001121",
"normalized_example_id": "ex_001121",
"source_idx": 1121,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1978,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{1347}",
"budget": 1758
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001123",
"normalized_example_id": "ex_001123",
"source_idx": 1123,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{1347}",
"budget": 2344
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001123",
"normalized_example_id": "ex_001123",
"source_idx": 1123,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}{1347}",
"budget": 2930
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001123",
"normalized_example_id": "ex_001123",
"source_idx": 1123,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2930,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x^2-\\ln|x|+\\frac{1}{9}\\ln|x-4|-\\frac{1}{9}\\ln|x+5|+C",
"budget": 1332
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001126",
"normalized_example_id": "ex_001126",
"source_idx": 1126,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2220,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x^2-\\ln|x|+\\frac{1}{9}\\ln|x-4|-\\frac{1}{9}\\ln|x+5|+C",
"budget": 1776
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001126",
"normalized_example_id": "ex_001126",
"source_idx": 1126,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2220,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x^2-\\ln|x|+\\frac{1}{9}\\ln|x-4|-\\frac{1}{9}\\ln|x+5|+C",
"budget": 2220
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001126",
"normalized_example_id": "ex_001126",
"source_idx": 1126,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2220,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 883
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001127",
"normalized_example_id": "ex_001127",
"source_idx": 1127,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1471,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1177
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001127",
"normalized_example_id": "ex_001127",
"source_idx": 1127,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1471,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1471
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001127",
"normalized_example_id": "ex_001127",
"source_idx": 1127,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1471,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{195}{512}",
"budget": 2610
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001130",
"normalized_example_id": "ex_001130",
"source_idx": 1130,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4350,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{195}{512}",
"budget": 3480
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001130",
"normalized_example_id": "ex_001130",
"source_idx": 1130,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4350,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{195}{512}",
"budget": 4350
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001130",
"normalized_example_id": "ex_001130",
"source_idx": 1130,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4350,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 1720
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001132",
"normalized_example_id": "ex_001132",
"source_idx": 1132,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 2294
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001132",
"normalized_example_id": "ex_001132",
"source_idx": 1132,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7",
"budget": 2867
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001132",
"normalized_example_id": "ex_001132",
"source_idx": 1132,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2867,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 1832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001133",
"normalized_example_id": "ex_001133",
"source_idx": 1133,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3054,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 2443
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001133",
"normalized_example_id": "ex_001133",
"source_idx": 1133,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3054,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 3054
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001133",
"normalized_example_id": "ex_001133",
"source_idx": 1133,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3054,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "135",
"budget": 3285
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001134",
"normalized_example_id": "ex_001134",
"source_idx": 1134,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5475,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "135",
"budget": 4380
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001134",
"normalized_example_id": "ex_001134",
"source_idx": 1134,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5475,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "135",
"budget": 5475
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001134",
"normalized_example_id": "ex_001134",
"source_idx": 1134,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5475,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 4949
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001135",
"normalized_example_id": "ex_001135",
"source_idx": 1135,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8248,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 6598
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001135",
"normalized_example_id": "ex_001135",
"source_idx": 1135,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8248,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "120",
"budget": 8248
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001135",
"normalized_example_id": "ex_001135",
"source_idx": 1135,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8248,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4235
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001139",
"normalized_example_id": "ex_001139",
"source_idx": 1139,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7058,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5646
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001139",
"normalized_example_id": "ex_001139",
"source_idx": 1139,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7058,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7058
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001139",
"normalized_example_id": "ex_001139",
"source_idx": 1139,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7058,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "456",
"budget": 961
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001143",
"normalized_example_id": "ex_001143",
"source_idx": 1143,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1602,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "456",
"budget": 1282
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001143",
"normalized_example_id": "ex_001143",
"source_idx": 1143,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1602,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "456",
"budget": 1602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001143",
"normalized_example_id": "ex_001143",
"source_idx": 1143,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1602,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "80",
"budget": 5812
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001144",
"normalized_example_id": "ex_001144",
"source_idx": 1144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "80",
"budget": 7749
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001144",
"normalized_example_id": "ex_001144",
"source_idx": 1144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "80",
"budget": 9686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001144",
"normalized_example_id": "ex_001144",
"source_idx": 1144,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9686,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{14}{33}",
"budget": 1602
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001145",
"normalized_example_id": "ex_001145",
"source_idx": 1145,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2670,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{14}{33}",
"budget": 2136
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001145",
"normalized_example_id": "ex_001145",
"source_idx": 1145,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2670,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{14}{33}",
"budget": 2670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_001145",
"normalized_example_id": "ex_001145",
"source_idx": 1145,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2670,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.