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": "90",
"budget": 3034
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006271",
"normalized_example_id": "ex_006271",
"source_idx": 6271,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3792,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "90",
"budget": 3792
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006271",
"normalized_example_id": "ex_006271",
"source_idx": 6271,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3792,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "253512",
"budget": 2064
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006273",
"normalized_example_id": "ex_006273",
"source_idx": 6273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3440,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "253512",
"budget": 2752
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006273",
"normalized_example_id": "ex_006273",
"source_idx": 6273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3440,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "253512",
"budget": 3440
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006273",
"normalized_example_id": "ex_006273",
"source_idx": 6273,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3440,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "360",
"budget": 2371
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006274",
"normalized_example_id": "ex_006274",
"source_idx": 6274,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3951,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "360",
"budget": 3161
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006274",
"normalized_example_id": "ex_006274",
"source_idx": 6274,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3951,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "360",
"budget": 3951
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006274",
"normalized_example_id": "ex_006274",
"source_idx": 6274,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3951,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{\\sqrt{3}}{3}",
"budget": 1684
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006275",
"normalized_example_id": "ex_006275",
"source_idx": 6275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2245
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006275",
"normalized_example_id": "ex_006275",
"source_idx": 6275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2806
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006275",
"normalized_example_id": "ex_006275",
"source_idx": 6275,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2806,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 2909
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006276",
"normalized_example_id": "ex_006276",
"source_idx": 6276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4849,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 3879
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006276",
"normalized_example_id": "ex_006276",
"source_idx": 6276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4849,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 4849
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006276",
"normalized_example_id": "ex_006276",
"source_idx": 6276,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4849,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 1466
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006281",
"normalized_example_id": "ex_006281",
"source_idx": 6281,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2443,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 1954
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006281",
"normalized_example_id": "ex_006281",
"source_idx": 6281,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2443,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "32",
"budget": 2443
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006281",
"normalized_example_id": "ex_006281",
"source_idx": 6281,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2443,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2019",
"budget": 785
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006283",
"normalized_example_id": "ex_006283",
"source_idx": 6283,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1308,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2019",
"budget": 1046
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006283",
"normalized_example_id": "ex_006283",
"source_idx": 6283,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1308,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2019",
"budget": 1308
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006283",
"normalized_example_id": "ex_006283",
"source_idx": 6283,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1308,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4\\,",
"budget": 2726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006284",
"normalized_example_id": "ex_006284",
"source_idx": 6284,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4\\,",
"budget": 3634
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006284",
"normalized_example_id": "ex_006284",
"source_idx": 6284,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4\\,",
"budget": 4543
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006284",
"normalized_example_id": "ex_006284",
"source_idx": 6284,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4543,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4316
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006285",
"normalized_example_id": "ex_006285",
"source_idx": 6285,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7194,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5755
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006285",
"normalized_example_id": "ex_006285",
"source_idx": 6285,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7194,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7194
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006285",
"normalized_example_id": "ex_006285",
"source_idx": 6285,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7194,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{CU^{2}(\\varepsilon-1)^{2}}{2\\varepsilon(\\varepsilon+1)}",
"budget": 2620
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006286",
"normalized_example_id": "ex_006286",
"source_idx": 6286,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4366,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{CU^{2}(\\varepsilon-1)^{2}}{2\\varepsilon(\\varepsilon+1)}",
"budget": 3493
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006286",
"normalized_example_id": "ex_006286",
"source_idx": 6286,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4366,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{CU^{2}(\\varepsilon-1)^{2}}{2\\varepsilon(\\varepsilon+1)}",
"budget": 4366
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006286",
"normalized_example_id": "ex_006286",
"source_idx": 6286,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4366,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 3412
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006287",
"normalized_example_id": "ex_006287",
"source_idx": 6287,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5687,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 4550
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006287",
"normalized_example_id": "ex_006287",
"source_idx": 6287,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5687,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25",
"budget": 5687
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006287",
"normalized_example_id": "ex_006287",
"source_idx": 6287,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5687,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 4217
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006288",
"normalized_example_id": "ex_006288",
"source_idx": 6288,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7029,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 5623
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006288",
"normalized_example_id": "ex_006288",
"source_idx": 6288,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7029,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "432",
"budget": 7029
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006288",
"normalized_example_id": "ex_006288",
"source_idx": 6288,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7029,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "517",
"budget": 2342
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006291",
"normalized_example_id": "ex_006291",
"source_idx": 6291,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3903,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "517",
"budget": 3122
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006291",
"normalized_example_id": "ex_006291",
"source_idx": 6291,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3903,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "517",
"budget": 3903
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006291",
"normalized_example_id": "ex_006291",
"source_idx": 6291,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3903,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{1}{3}",
"budget": 4343
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006295",
"normalized_example_id": "ex_006295",
"source_idx": 6295,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7238,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{1}{3}",
"budget": 5790
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006295",
"normalized_example_id": "ex_006295",
"source_idx": 6295,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7238,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\arccos\\frac{1}{3}",
"budget": 7238
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006295",
"normalized_example_id": "ex_006295",
"source_idx": 6295,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7238,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(P) = 0",
"budget": 4499
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006296",
"normalized_example_id": "ex_006296",
"source_idx": 6296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7498,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(P) = 0",
"budget": 5998
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006296",
"normalized_example_id": "ex_006296",
"source_idx": 6296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7498,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(P) = 0",
"budget": 7498
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006296",
"normalized_example_id": "ex_006296",
"source_idx": 6296,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7498,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4208
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006297",
"normalized_example_id": "ex_006297",
"source_idx": 6297,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7013,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5610
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006297",
"normalized_example_id": "ex_006297",
"source_idx": 6297,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7013,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7013
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006297",
"normalized_example_id": "ex_006297",
"source_idx": 6297,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7013,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 3940
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006298",
"normalized_example_id": "ex_006298",
"source_idx": 6298,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6566,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 5253
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006298",
"normalized_example_id": "ex_006298",
"source_idx": 6298,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6566,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "21",
"budget": 6566
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006298",
"normalized_example_id": "ex_006298",
"source_idx": 6298,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6566,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2731
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006300",
"normalized_example_id": "ex_006300",
"source_idx": 6300,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3641
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006300",
"normalized_example_id": "ex_006300",
"source_idx": 6300,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4551
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006300",
"normalized_example_id": "ex_006300",
"source_idx": 6300,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4551,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1or3",
"budget": 4915
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006302",
"normalized_example_id": "ex_006302",
"source_idx": 6302,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8191,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1or3",
"budget": 6553
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006302",
"normalized_example_id": "ex_006302",
"source_idx": 6302,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8191,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1or3",
"budget": 8191
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006302",
"normalized_example_id": "ex_006302",
"source_idx": 6302,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8191,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2}",
"budget": 812
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006304",
"normalized_example_id": "ex_006304",
"source_idx": 6304,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1354,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2}",
"budget": 1083
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006304",
"normalized_example_id": "ex_006304",
"source_idx": 6304,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1354,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{2}",
"budget": 1354
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006304",
"normalized_example_id": "ex_006304",
"source_idx": 6304,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1354,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "143",
"budget": 1115
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006308",
"normalized_example_id": "ex_006308",
"source_idx": 6308,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1858,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "143",
"budget": 1486
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006308",
"normalized_example_id": "ex_006308",
"source_idx": 6308,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1858,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "143",
"budget": 1858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006308",
"normalized_example_id": "ex_006308",
"source_idx": 6308,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1858,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{17}{21}",
"budget": 1556
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006309",
"normalized_example_id": "ex_006309",
"source_idx": 6309,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2594,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{17}{21}",
"budget": 2075
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006309",
"normalized_example_id": "ex_006309",
"source_idx": 6309,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2594,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{17}{21}",
"budget": 2594
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006309",
"normalized_example_id": "ex_006309",
"source_idx": 6309,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2594,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2700",
"budget": 5077
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006310",
"normalized_example_id": "ex_006310",
"source_idx": 6310,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8461,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2700",
"budget": 6769
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006310",
"normalized_example_id": "ex_006310",
"source_idx": 6310,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8461,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "2700",
"budget": 8461
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006310",
"normalized_example_id": "ex_006310",
"source_idx": 6310,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8461,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 2230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006311",
"normalized_example_id": "ex_006311",
"source_idx": 6311,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3717,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 2974
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006311",
"normalized_example_id": "ex_006311",
"source_idx": 6311,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3717,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "192",
"budget": 3717
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006311",
"normalized_example_id": "ex_006311",
"source_idx": 6311,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3717,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4002
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006312",
"normalized_example_id": "ex_006312",
"source_idx": 6312,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6670,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5336
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006312",
"normalized_example_id": "ex_006312",
"source_idx": 6312,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6670,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6670
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006312",
"normalized_example_id": "ex_006312",
"source_idx": 6312,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6670,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=4, y=6",
"budget": 3162
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006313",
"normalized_example_id": "ex_006313",
"source_idx": 6313,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5270,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=4, y=6",
"budget": 4216
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006313",
"normalized_example_id": "ex_006313",
"source_idx": 6313,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5270,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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=4, y=6",
"budget": 5270
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006313",
"normalized_example_id": "ex_006313",
"source_idx": 6313,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5270,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 4385
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006318",
"normalized_example_id": "ex_006318",
"source_idx": 6318,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7309,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 5847
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006318",
"normalized_example_id": "ex_006318",
"source_idx": 6318,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7309,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "4",
"budget": 7309
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006318",
"normalized_example_id": "ex_006318",
"source_idx": 6318,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7309,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3874
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006320",
"normalized_example_id": "ex_006320",
"source_idx": 6320,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6456,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5165
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006320",
"normalized_example_id": "ex_006320",
"source_idx": 6320,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6456,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6456
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006320",
"normalized_example_id": "ex_006320",
"source_idx": 6320,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6456,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7381",
"budget": 4505
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006321",
"normalized_example_id": "ex_006321",
"source_idx": 6321,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7509,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7381",
"budget": 6007
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006321",
"normalized_example_id": "ex_006321",
"source_idx": 6321,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7509,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7381",
"budget": 7509
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006321",
"normalized_example_id": "ex_006321",
"source_idx": 6321,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7509,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "316",
"budget": 4686
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006322",
"normalized_example_id": "ex_006322",
"source_idx": 6322,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7810,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "316",
"budget": 6248
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006322",
"normalized_example_id": "ex_006322",
"source_idx": 6322,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7810,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "316",
"budget": 7810
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006322",
"normalized_example_id": "ex_006322",
"source_idx": 6322,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7810,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{5}",
"budget": 911
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006324",
"normalized_example_id": "ex_006324",
"source_idx": 6324,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1519,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{5}",
"budget": 1215
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006324",
"normalized_example_id": "ex_006324",
"source_idx": 6324,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1519,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{4}{5}",
"budget": 1519
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006324",
"normalized_example_id": "ex_006324",
"source_idx": 6324,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1519,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{40}{119}",
"budget": 1070
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006325",
"normalized_example_id": "ex_006325",
"source_idx": 6325,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{40}{119}",
"budget": 1426
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006325",
"normalized_example_id": "ex_006325",
"source_idx": 6325,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{40}{119}",
"budget": 1783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006325",
"normalized_example_id": "ex_006325",
"source_idx": 6325,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1783,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 944
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006326",
"normalized_example_id": "ex_006326",
"source_idx": 6326,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1573,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1258
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006326",
"normalized_example_id": "ex_006326",
"source_idx": 6326,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1573,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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",
"budget": 1573
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006326",
"normalized_example_id": "ex_006326",
"source_idx": 6326,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1573,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 2290
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006328",
"normalized_example_id": "ex_006328",
"source_idx": 6328,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3816,
... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "3",
"budget": 3053
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_006328",
"normalized_example_id": "ex_006328",
"source_idx": 6328,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3816,
... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.