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": "9.9",
"budget": 8433
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002563",
"normalized_example_id": "ex_002563",
"source_idx": 2563,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8433,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1490
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002564",
"normalized_example_id": "ex_002564",
"source_idx": 2564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1987
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002564",
"normalized_example_id": "ex_002564",
"source_idx": 2564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2484
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002564",
"normalized_example_id": "ex_002564",
"source_idx": 2564,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2484,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5899
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002565",
"normalized_example_id": "ex_002565",
"source_idx": 2565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9832,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7866
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002565",
"normalized_example_id": "ex_002565",
"source_idx": 2565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9832,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9832
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002565",
"normalized_example_id": "ex_002565",
"source_idx": 2565,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9832,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "600",
"budget": 2024
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002568",
"normalized_example_id": "ex_002568",
"source_idx": 2568,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3373,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "600",
"budget": 2698
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002568",
"normalized_example_id": "ex_002568",
"source_idx": 2568,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3373,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "600",
"budget": 3373
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002568",
"normalized_example_id": "ex_002568",
"source_idx": 2568,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3373,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2750
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002570",
"normalized_example_id": "ex_002570",
"source_idx": 2570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4584,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3667
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002570",
"normalized_example_id": "ex_002570",
"source_idx": 2570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4584,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4584
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002570",
"normalized_example_id": "ex_002570",
"source_idx": 2570,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4584,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "b = 9, c = 14",
"budget": 5765
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002572",
"normalized_example_id": "ex_002572",
"source_idx": 2572,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9609,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "b = 9, c = 14",
"budget": 7687
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002572",
"normalized_example_id": "ex_002572",
"source_idx": 2572,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9609,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "b = 9, c = 14",
"budget": 9609
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002572",
"normalized_example_id": "ex_002572",
"source_idx": 2572,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9609,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15\\mathrm{~}",
"budget": 4347
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002573",
"normalized_example_id": "ex_002573",
"source_idx": 2573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7245,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15\\mathrm{~}",
"budget": 5796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002573",
"normalized_example_id": "ex_002573",
"source_idx": 2573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7245,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "15\\mathrm{~}",
"budget": 7245
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002573",
"normalized_example_id": "ex_002573",
"source_idx": 2573,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7245,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{8}",
"budget": 4337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002574",
"normalized_example_id": "ex_002574",
"source_idx": 2574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{8}",
"budget": 5782
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002574",
"normalized_example_id": "ex_002574",
"source_idx": 2574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{8}",
"budget": 7228
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002574",
"normalized_example_id": "ex_002574",
"source_idx": 2574,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7228,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1474
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002575",
"normalized_example_id": "ex_002575",
"source_idx": 2575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2457,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1966
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002575",
"normalized_example_id": "ex_002575",
"source_idx": 2575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2457,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2457
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002575",
"normalized_example_id": "ex_002575",
"source_idx": 2575,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2457,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}",
"budget": 1051
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002579",
"normalized_example_id": "ex_002579",
"source_idx": 2579,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}",
"budget": 1402
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002579",
"normalized_example_id": "ex_002579",
"source_idx": 2579,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2}",
"budget": 1752
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002579",
"normalized_example_id": "ex_002579",
"source_idx": 2579,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1752,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14763",
"budget": 3757
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002584",
"normalized_example_id": "ex_002584",
"source_idx": 2584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6261,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14763",
"budget": 5009
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002584",
"normalized_example_id": "ex_002584",
"source_idx": 2584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6261,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "14763",
"budget": 6261
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002584",
"normalized_example_id": "ex_002584",
"source_idx": 2584,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6261,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{isn't possible to go from}\\ x^2+4x+3\\ \\text{to}\\ x^2+10x+9",
"budget": 2953
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002585",
"normalized_example_id": "ex_002585",
"source_idx": 2585,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4921,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{isn't possible to go from}\\ x^2+4x+3\\ \\text{to}\\ x^2+10x+9",
"budget": 3937
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002585",
"normalized_example_id": "ex_002585",
"source_idx": 2585,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4921,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\text{isn't possible to go from}\\ x^2+4x+3\\ \\text{to}\\ x^2+10x+9",
"budget": 4921
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002585",
"normalized_example_id": "ex_002585",
"source_idx": 2585,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4921,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 2528
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002590",
"normalized_example_id": "ex_002590",
"source_idx": 2590,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4213,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 3370
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002590",
"normalized_example_id": "ex_002590",
"source_idx": 2590,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4213,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "40",
"budget": 4213
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002590",
"normalized_example_id": "ex_002590",
"source_idx": 2590,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4213,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 949
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002591",
"normalized_example_id": "ex_002591",
"source_idx": 2591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1581,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1265
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002591",
"normalized_example_id": "ex_002591",
"source_idx": 2591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1581,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1581
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002591",
"normalized_example_id": "ex_002591",
"source_idx": 2591,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1581,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "43",
"budget": 1118
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002592",
"normalized_example_id": "ex_002592",
"source_idx": 2592,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1864,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "43",
"budget": 1491
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002592",
"normalized_example_id": "ex_002592",
"source_idx": 2592,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1864,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "43",
"budget": 1864
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002592",
"normalized_example_id": "ex_002592",
"source_idx": 2592,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1864,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = x",
"budget": 4838
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002593",
"normalized_example_id": "ex_002593",
"source_idx": 2593,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8064,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = x",
"budget": 6451
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002593",
"normalized_example_id": "ex_002593",
"source_idx": 2593,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8064,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "f(x) = x",
"budget": 8064
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002593",
"normalized_example_id": "ex_002593",
"source_idx": 2593,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8064,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4119
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002594",
"normalized_example_id": "ex_002594",
"source_idx": 2594,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6865,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5492
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002594",
"normalized_example_id": "ex_002594",
"source_idx": 2594,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6865,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6865
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002594",
"normalized_example_id": "ex_002594",
"source_idx": 2594,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6865,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4153
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002599",
"normalized_example_id": "ex_002599",
"source_idx": 2599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6922,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5538
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002599",
"normalized_example_id": "ex_002599",
"source_idx": 2599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6922,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 6922
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002599",
"normalized_example_id": "ex_002599",
"source_idx": 2599,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6922,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 1130
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002602",
"normalized_example_id": "ex_002602",
"source_idx": 2602,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1883,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 1506
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002602",
"normalized_example_id": "ex_002602",
"source_idx": 2602,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1883,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "16",
"budget": 1883
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002602",
"normalized_example_id": "ex_002602",
"source_idx": 2602,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1883,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{25}{2}",
"budget": 5438
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002603",
"normalized_example_id": "ex_002603",
"source_idx": 2603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9063,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{25}{2}",
"budget": 7250
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002603",
"normalized_example_id": "ex_002603",
"source_idx": 2603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9063,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{25}{2}",
"budget": 9063
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002603",
"normalized_example_id": "ex_002603",
"source_idx": 2603,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9063,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 646
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002608",
"normalized_example_id": "ex_002608",
"source_idx": 2608,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1077,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 862
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002608",
"normalized_example_id": "ex_002608",
"source_idx": 2608,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1077,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "11",
"budget": 1077
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002608",
"normalized_example_id": "ex_002608",
"source_idx": 2608,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1077,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 1659
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002609",
"normalized_example_id": "ex_002609",
"source_idx": 2609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2765,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 2212
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002609",
"normalized_example_id": "ex_002609",
"source_idx": 2609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2765,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 2765
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002609",
"normalized_example_id": "ex_002609",
"source_idx": 2609,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2765,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3000",
"budget": 802
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002611",
"normalized_example_id": "ex_002611",
"source_idx": 2611,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3000",
"budget": 1070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002611",
"normalized_example_id": "ex_002611",
"source_idx": 2611,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3000",
"budget": 1337
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002611",
"normalized_example_id": "ex_002611",
"source_idx": 2611,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1337,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 666
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002612",
"normalized_example_id": "ex_002612",
"source_idx": 2612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 888
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002612",
"normalized_example_id": "ex_002612",
"source_idx": 2612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1110
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002612",
"normalized_example_id": "ex_002612",
"source_idx": 2612,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1110,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1456
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002616",
"normalized_example_id": "ex_002616",
"source_idx": 2616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2427,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1942
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002616",
"normalized_example_id": "ex_002616",
"source_idx": 2616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2427,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2427
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002616",
"normalized_example_id": "ex_002616",
"source_idx": 2616,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2427,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91,85,79",
"budget": 1375
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002617",
"normalized_example_id": "ex_002617",
"source_idx": 2617,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2292,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91,85,79",
"budget": 1834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002617",
"normalized_example_id": "ex_002617",
"source_idx": 2617,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2292,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "91,85,79",
"budget": 2292
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002617",
"normalized_example_id": "ex_002617",
"source_idx": 2617,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2292,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{8}",
"budget": 2892
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002618",
"normalized_example_id": "ex_002618",
"source_idx": 2618,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4820,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{8}",
"budget": 3856
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002618",
"normalized_example_id": "ex_002618",
"source_idx": 2618,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4820,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{8}",
"budget": 4820
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002618",
"normalized_example_id": "ex_002618",
"source_idx": 2618,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4820,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3 \\sqrt{3}}{4}",
"budget": 4802
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002619",
"normalized_example_id": "ex_002619",
"source_idx": 2619,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3 \\sqrt{3}}{4}",
"budget": 6402
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002619",
"normalized_example_id": "ex_002619",
"source_idx": 2619,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{3 \\sqrt{3}}{4}",
"budget": 8003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002619",
"normalized_example_id": "ex_002619",
"source_idx": 2619,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8003,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(A) } T = 2T_0 \\text{ regardless of the value of } \\theta_0",
"budget": 3205
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002622",
"normalized_example_id": "ex_002622",
"source_idx": 2622,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5341,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(A) } T = 2T_0 \\text{ regardless of the value of } \\theta_0",
"budget": 4273
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002622",
"normalized_example_id": "ex_002622",
"source_idx": 2622,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5341,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\textbf{(A) } T = 2T_0 \\text{ regardless of the value of } \\theta_0",
"budget": 5341
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002622",
"normalized_example_id": "ex_002622",
"source_idx": 2622,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5341,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,3),(3,13),(13,3)",
"budget": 5286
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002623",
"normalized_example_id": "ex_002623",
"source_idx": 2623,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8810,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,3),(3,13),(13,3)",
"budget": 7048
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002623",
"normalized_example_id": "ex_002623",
"source_idx": 2623,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8810,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "(3,3),(3,13),(13,3)",
"budget": 8810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002623",
"normalized_example_id": "ex_002623",
"source_idx": 2623,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8810,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1024
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002629",
"normalized_example_id": "ex_002629",
"source_idx": 2629,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002629",
"normalized_example_id": "ex_002629",
"source_idx": 2629,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "8",
"budget": 1707
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002629",
"normalized_example_id": "ex_002629",
"source_idx": 2629,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1707,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2055
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002630",
"normalized_example_id": "ex_002630",
"source_idx": 2630,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2740
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002630",
"normalized_example_id": "ex_002630",
"source_idx": 2630,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3425
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002630",
"normalized_example_id": "ex_002630",
"source_idx": 2630,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3425,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 4",
"budget": 5800
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002632",
"normalized_example_id": "ex_002632",
"source_idx": 2632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9667,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 4",
"budget": 7734
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002632",
"normalized_example_id": "ex_002632",
"source_idx": 2632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9667,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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 = 4",
"budget": 9667
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002632",
"normalized_example_id": "ex_002632",
"source_idx": 2632,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9667,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n}+2n-1",
"budget": 1520
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002633",
"normalized_example_id": "ex_002633",
"source_idx": 2633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2534,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n}+2n-1",
"budget": 2027
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002633",
"normalized_example_id": "ex_002633",
"source_idx": 2633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2534,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{n}+2n-1",
"budget": 2534
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002633",
"normalized_example_id": "ex_002633",
"source_idx": 2633,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2534,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.