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": "(2;1)",
"budget": 1640
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002453",
"normalized_example_id": "ex_002453",
"source_idx": 2453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2733,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;1)",
"budget": 2186
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002453",
"normalized_example_id": "ex_002453",
"source_idx": 2453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2733,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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;1)",
"budget": 2733
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002453",
"normalized_example_id": "ex_002453",
"source_idx": 2453,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2733,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1617
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002455",
"normalized_example_id": "ex_002455",
"source_idx": 2455,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2695,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2156
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002455",
"normalized_example_id": "ex_002455",
"source_idx": 2455,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2695,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 2695
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002455",
"normalized_example_id": "ex_002455",
"source_idx": 2455,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2695,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "55",
"budget": 2794
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002456",
"normalized_example_id": "ex_002456",
"source_idx": 2456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "55",
"budget": 3726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002456",
"normalized_example_id": "ex_002456",
"source_idx": 2456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "55",
"budget": 4657
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002456",
"normalized_example_id": "ex_002456",
"source_idx": 2456,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4657,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_{1}=1,y_{1}=4;x_{2}=1,y_{2}=-4;x_{3}=4,y_{3}=1;x_{4}=-4,y_{4}=1",
"budget": 1075
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002457",
"normalized_example_id": "ex_002457",
"source_idx": 2457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1792,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_{1}=1,y_{1}=4;x_{2}=1,y_{2}=-4;x_{3}=4,y_{3}=1;x_{4}=-4,y_{4}=1",
"budget": 1434
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002457",
"normalized_example_id": "ex_002457",
"source_idx": 2457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1792,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "x_{1}=1,y_{1}=4;x_{2}=1,y_{2}=-4;x_{3}=4,y_{3}=1;x_{4}=-4,y_{4}=1",
"budget": 1792
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002457",
"normalized_example_id": "ex_002457",
"source_idx": 2457,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1792,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,000,000",
"budget": 2215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002458",
"normalized_example_id": "ex_002458",
"source_idx": 2458,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3691,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,000,000",
"budget": 2953
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002458",
"normalized_example_id": "ex_002458",
"source_idx": 2458,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3691,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1,000,000",
"budget": 3691
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002458",
"normalized_example_id": "ex_002458",
"source_idx": 2458,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3691,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002459",
"normalized_example_id": "ex_002459",
"source_idx": 2459,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1469,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 1175
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002459",
"normalized_example_id": "ex_002459",
"source_idx": 2459,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1469,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "44",
"budget": 1469
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002459",
"normalized_example_id": "ex_002459",
"source_idx": 2459,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1469,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{x^{2}}{64}(2x-1)^{32}-\\frac{x}{2112}(2x-1)^{33}+\\frac{(2x-1)^{34}}{143616}+C",
"budget": 3367
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002460",
"normalized_example_id": "ex_002460",
"source_idx": 2460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{x^{2}}{64}(2x-1)^{32}-\\frac{x}{2112}(2x-1)^{33}+\\frac{(2x-1)^{34}}{143616}+C",
"budget": 4490
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002460",
"normalized_example_id": "ex_002460",
"source_idx": 2460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{x^{2}}{64}(2x-1)^{32}-\\frac{x}{2112}(2x-1)^{33}+\\frac{(2x-1)^{34}}{143616}+C",
"budget": 5612
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002460",
"normalized_example_id": "ex_002460",
"source_idx": 2460,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5612,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "67",
"budget": 2520
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002461",
"normalized_example_id": "ex_002461",
"source_idx": 2461,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4200,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "67",
"budget": 3360
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002461",
"normalized_example_id": "ex_002461",
"source_idx": 2461,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4200,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "67",
"budget": 4200
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002461",
"normalized_example_id": "ex_002461",
"source_idx": 2461,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4200,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2205
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002462",
"normalized_example_id": "ex_002462",
"source_idx": 2462,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3675,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 2940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002462",
"normalized_example_id": "ex_002462",
"source_idx": 2462,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3675,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12",
"budget": 3675
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002462",
"normalized_example_id": "ex_002462",
"source_idx": 2462,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3675,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{3}",
"budget": 938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002465",
"normalized_example_id": "ex_002465",
"source_idx": 2465,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1563,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{3}",
"budget": 1250
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002465",
"normalized_example_id": "ex_002465",
"source_idx": 2465,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1563,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\sqrt{3}}{3}",
"budget": 1563
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002465",
"normalized_example_id": "ex_002465",
"source_idx": 2465,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1563,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.4\\mathrm{~}",
"budget": 2196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002466",
"normalized_example_id": "ex_002466",
"source_idx": 2466,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.4\\mathrm{~}",
"budget": 2928
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002466",
"normalized_example_id": "ex_002466",
"source_idx": 2466,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2.4\\mathrm{~}",
"budget": 3660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002466",
"normalized_example_id": "ex_002466",
"source_idx": 2466,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{10} \\cdot 3^{10}",
"budget": 2252
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002467",
"normalized_example_id": "ex_002467",
"source_idx": 2467,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{10} \\cdot 3^{10}",
"budget": 3003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002467",
"normalized_example_id": "ex_002467",
"source_idx": 2467,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{10} \\cdot 3^{10}",
"budget": 3754
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002467",
"normalized_example_id": "ex_002467",
"source_idx": 2467,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3754,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2007 + \\frac{\\pi}{2}",
"budget": 2774
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002470",
"normalized_example_id": "ex_002470",
"source_idx": 2470,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2007 + \\frac{\\pi}{2}",
"budget": 3698
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002470",
"normalized_example_id": "ex_002470",
"source_idx": 2470,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2007 + \\frac{\\pi}{2}",
"budget": 4623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002470",
"normalized_example_id": "ex_002470",
"source_idx": 2470,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4623,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 984
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002471",
"normalized_example_id": "ex_002471",
"source_idx": 2471,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1640,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1312
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002471",
"normalized_example_id": "ex_002471",
"source_idx": 2471,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1640,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1640
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002471",
"normalized_example_id": "ex_002471",
"source_idx": 2471,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1640,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{11}{7}",
"budget": 3950
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002472",
"normalized_example_id": "ex_002472",
"source_idx": 2472,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6583,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{11}{7}",
"budget": 5266
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002472",
"normalized_example_id": "ex_002472",
"source_idx": 2472,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6583,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{11}{7}",
"budget": 6583
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002472",
"normalized_example_id": "ex_002472",
"source_idx": 2472,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6583,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3575880",
"budget": 2543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002478",
"normalized_example_id": "ex_002478",
"source_idx": 2478,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4239,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3575880",
"budget": 3391
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002478",
"normalized_example_id": "ex_002478",
"source_idx": 2478,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4239,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3575880",
"budget": 4239
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002478",
"normalized_example_id": "ex_002478",
"source_idx": 2478,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4239,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19,24,21,23,20,22",
"budget": 621
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002479",
"normalized_example_id": "ex_002479",
"source_idx": 2479,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1035,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19,24,21,23,20,22",
"budget": 828
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002479",
"normalized_example_id": "ex_002479",
"source_idx": 2479,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1035,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "19,24,21,23,20,22",
"budget": 1035
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002479",
"normalized_example_id": "ex_002479",
"source_idx": 2479,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1035,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "942",
"budget": 1526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002481",
"normalized_example_id": "ex_002481",
"source_idx": 2481,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "942",
"budget": 2034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002481",
"normalized_example_id": "ex_002481",
"source_idx": 2481,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "942",
"budget": 2543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002481",
"normalized_example_id": "ex_002481",
"source_idx": 2481,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4245
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002483",
"normalized_example_id": "ex_002483",
"source_idx": 2483,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002483",
"normalized_example_id": "ex_002483",
"source_idx": 2483,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7075
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002483",
"normalized_example_id": "ex_002483",
"source_idx": 2483,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7075,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-10",
"budget": 2296
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002485",
"normalized_example_id": "ex_002485",
"source_idx": 2485,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3826,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-10",
"budget": 3061
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002485",
"normalized_example_id": "ex_002485",
"source_idx": 2485,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3826,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-10",
"budget": 3826
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002485",
"normalized_example_id": "ex_002485",
"source_idx": 2485,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3826,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 1732
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002487",
"normalized_example_id": "ex_002487",
"source_idx": 2487,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2886,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2309
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002487",
"normalized_example_id": "ex_002487",
"source_idx": 2487,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2886,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "10",
"budget": 2886
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002487",
"normalized_example_id": "ex_002487",
"source_idx": 2487,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2886,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{61}",
"budget": 842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002488",
"normalized_example_id": "ex_002488",
"source_idx": 2488,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1403,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{61}",
"budget": 1122
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002488",
"normalized_example_id": "ex_002488",
"source_idx": 2488,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1403,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\sqrt{61}",
"budget": 1403
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002488",
"normalized_example_id": "ex_002488",
"source_idx": 2488,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1403,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4982
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002489",
"normalized_example_id": "ex_002489",
"source_idx": 2489,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8304,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6643
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002489",
"normalized_example_id": "ex_002489",
"source_idx": 2489,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8304,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8304
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002489",
"normalized_example_id": "ex_002489",
"source_idx": 2489,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8304,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{2}+3x+2",
"budget": 1187
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002491",
"normalized_example_id": "ex_002491",
"source_idx": 2491,
"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": "f(x)=x^{2}+3x+2",
"budget": 1582
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002491",
"normalized_example_id": "ex_002491",
"source_idx": 2491,
"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": "f(x)=x^{2}+3x+2",
"budget": 1978
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002491",
"normalized_example_id": "ex_002491",
"source_idx": 2491,
"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": "225625",
"budget": 4973
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002495",
"normalized_example_id": "ex_002495",
"source_idx": 2495,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "225625",
"budget": 6630
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002495",
"normalized_example_id": "ex_002495",
"source_idx": 2495,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "225625",
"budget": 8288
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002495",
"normalized_example_id": "ex_002495",
"source_idx": 2495,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8288,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M(X)=\\frac{1}{3},D(X)=\\frac{2}{9},\\sigma(X)=\\frac{\\sqrt{2}}{3}",
"budget": 834
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002496",
"normalized_example_id": "ex_002496",
"source_idx": 2496,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1390,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M(X)=\\frac{1}{3},D(X)=\\frac{2}{9},\\sigma(X)=\\frac{\\sqrt{2}}{3}",
"budget": 1112
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002496",
"normalized_example_id": "ex_002496",
"source_idx": 2496,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1390,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M(X)=\\frac{1}{3},D(X)=\\frac{2}{9},\\sigma(X)=\\frac{\\sqrt{2}}{3}",
"budget": 1390
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002496",
"normalized_example_id": "ex_002496",
"source_idx": 2496,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1390,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9or-9",
"budget": 1399
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002498",
"normalized_example_id": "ex_002498",
"source_idx": 2498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2331,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9or-9",
"budget": 1865
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002498",
"normalized_example_id": "ex_002498",
"source_idx": 2498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2331,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "9or-9",
"budget": 2331
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002498",
"normalized_example_id": "ex_002498",
"source_idx": 2498,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2331,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 3310
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002499",
"normalized_example_id": "ex_002499",
"source_idx": 2499,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5516,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 4413
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002499",
"normalized_example_id": "ex_002499",
"source_idx": 2499,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5516,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 5516
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002499",
"normalized_example_id": "ex_002499",
"source_idx": 2499,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5516,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "198",
"budget": 2155
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002500",
"normalized_example_id": "ex_002500",
"source_idx": 2500,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3592,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "198",
"budget": 2874
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002500",
"normalized_example_id": "ex_002500",
"source_idx": 2500,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3592,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "198",
"budget": 3592
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002500",
"normalized_example_id": "ex_002500",
"source_idx": 2500,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3592,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2-\\sqrt{3}}{8}",
"budget": 3491
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002501",
"normalized_example_id": "ex_002501",
"source_idx": 2501,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5819,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2-\\sqrt{3}}{8}",
"budget": 4655
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002501",
"normalized_example_id": "ex_002501",
"source_idx": 2501,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5819,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2-\\sqrt{3}}{8}",
"budget": 5819
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002501",
"normalized_example_id": "ex_002501",
"source_idx": 2501,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5819,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2416
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002502",
"normalized_example_id": "ex_002502",
"source_idx": 2502,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4026,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3221
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002502",
"normalized_example_id": "ex_002502",
"source_idx": 2502,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4026,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4026
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002502",
"normalized_example_id": "ex_002502",
"source_idx": 2502,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4026,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}{4}\\leqslantx\\leqslant\\frac{7}{4}\\pi",
"budget": 5796
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002504",
"normalized_example_id": "ex_002504",
"source_idx": 2504,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}{4}\\leqslantx\\leqslant\\frac{7}{4}\\pi",
"budget": 7728
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002504",
"normalized_example_id": "ex_002504",
"source_idx": 2504,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{\\pi}{4}\\leqslantx\\leqslant\\frac{7}{4}\\pi",
"budget": 9660
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002504",
"normalized_example_id": "ex_002504",
"source_idx": 2504,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9660,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M_{xy}=\\frac{1}{720},M_{yz}=\\frac{1}{360},M_{xz}=\\frac{1}{360}",
"budget": 3370
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002506",
"normalized_example_id": "ex_002506",
"source_idx": 2506,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5616,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M_{xy}=\\frac{1}{720},M_{yz}=\\frac{1}{360},M_{xz}=\\frac{1}{360}",
"budget": 4493
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002506",
"normalized_example_id": "ex_002506",
"source_idx": 2506,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5616,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "M_{xy}=\\frac{1}{720},M_{yz}=\\frac{1}{360},M_{xz}=\\frac{1}{360}",
"budget": 5616
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002506",
"normalized_example_id": "ex_002506",
"source_idx": 2506,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5616,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "39",
"budget": 4623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_002509",
"normalized_example_id": "ex_002509",
"source_idx": 2509,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7705,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.