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": "4",
"budget": 6553
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000651",
"normalized_example_id": "ex_000651",
"source_idx": 651,
"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": "4",
"budget": 8191
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000651",
"normalized_example_id": "ex_000651",
"source_idx": 651,
"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": "869",
"budget": 1259
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000653",
"normalized_example_id": "ex_000653",
"source_idx": 653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2099,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "869",
"budget": 1679
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000653",
"normalized_example_id": "ex_000653",
"source_idx": 653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2099,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "869",
"budget": 2099
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000653",
"normalized_example_id": "ex_000653",
"source_idx": 653,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2099,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 5617
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000654",
"normalized_example_id": "ex_000654",
"source_idx": 654,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9361,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 7489
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000654",
"normalized_example_id": "ex_000654",
"source_idx": 654,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9361,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "5",
"budget": 9361
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000654",
"normalized_example_id": "ex_000654",
"source_idx": 654,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9361,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{4}",
"budget": 1393
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000657",
"normalized_example_id": "ex_000657",
"source_idx": 657,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2322,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{4}",
"budget": 1858
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000657",
"normalized_example_id": "ex_000657",
"source_idx": 657,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2322,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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^{4}",
"budget": 2322
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000657",
"normalized_example_id": "ex_000657",
"source_idx": 657,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2322,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "666",
"budget": 842
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000658",
"normalized_example_id": "ex_000658",
"source_idx": 658,
"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": "666",
"budget": 1122
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000658",
"normalized_example_id": "ex_000658",
"source_idx": 658,
"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": "666",
"budget": 1403
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000658",
"normalized_example_id": "ex_000658",
"source_idx": 658,
"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": "11",
"budget": 4519
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000659",
"normalized_example_id": "ex_000659",
"source_idx": 659,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7532,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6026
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000659",
"normalized_example_id": "ex_000659",
"source_idx": 659,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7532,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7532
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000659",
"normalized_example_id": "ex_000659",
"source_idx": 659,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7532,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1502
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000661",
"normalized_example_id": "ex_000661",
"source_idx": 661,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2504,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2003
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000661",
"normalized_example_id": "ex_000661",
"source_idx": 661,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2504,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2504
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000661",
"normalized_example_id": "ex_000661",
"source_idx": 661,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2504,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27.5",
"budget": 4570
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000663",
"normalized_example_id": "ex_000663",
"source_idx": 663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7616,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27.5",
"budget": 6093
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000663",
"normalized_example_id": "ex_000663",
"source_idx": 663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7616,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "27.5",
"budget": 7616
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000663",
"normalized_example_id": "ex_000663",
"source_idx": 663,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7616,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2} \\sqrt{3 a^{2}+4 h^{2}}",
"budget": 2642
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000664",
"normalized_example_id": "ex_000664",
"source_idx": 664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4404,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2} \\sqrt{3 a^{2}+4 h^{2}}",
"budget": 3523
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000664",
"normalized_example_id": "ex_000664",
"source_idx": 664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4404,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "\\frac{1}{2} \\sqrt{3 a^{2}+4 h^{2}}",
"budget": 4404
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000664",
"normalized_example_id": "ex_000664",
"source_idx": 664,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4404,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3388
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000665",
"normalized_example_id": "ex_000665",
"source_idx": 665,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5647,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4518
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000665",
"normalized_example_id": "ex_000665",
"source_idx": 665,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5647,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000665",
"normalized_example_id": "ex_000665",
"source_idx": 665,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5647,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n)=\\frac{2^{n+1}+(-1)^{n}}{3}",
"budget": 1668
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000666",
"normalized_example_id": "ex_000666",
"source_idx": 666,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2780,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n)=\\frac{2^{n+1}+(-1)^{n}}{3}",
"budget": 2224
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000666",
"normalized_example_id": "ex_000666",
"source_idx": 666,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2780,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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(n)=\\frac{2^{n+1}+(-1)^{n}}{3}",
"budget": 2780
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000666",
"normalized_example_id": "ex_000666",
"source_idx": 666,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2780,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.64",
"budget": 990
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000667",
"normalized_example_id": "ex_000667",
"source_idx": 667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1650,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.64",
"budget": 1320
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000667",
"normalized_example_id": "ex_000667",
"source_idx": 667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1650,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "0.64",
"budget": 1650
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000667",
"normalized_example_id": "ex_000667",
"source_idx": 667,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1650,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 4726
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000668",
"normalized_example_id": "ex_000668",
"source_idx": 668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7876,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 6301
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000668",
"normalized_example_id": "ex_000668",
"source_idx": 668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7876,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "45",
"budget": 7876
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000668",
"normalized_example_id": "ex_000668",
"source_idx": 668,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7876,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5911
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000669",
"normalized_example_id": "ex_000669",
"source_idx": 669,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9851,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7881
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000669",
"normalized_example_id": "ex_000669",
"source_idx": 669,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9851,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 9851
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000669",
"normalized_example_id": "ex_000669",
"source_idx": 669,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 9851,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3718
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000674",
"normalized_example_id": "ex_000674",
"source_idx": 674,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6196,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4957
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000674",
"normalized_example_id": "ex_000674",
"source_idx": 674,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6196,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000674",
"normalized_example_id": "ex_000674",
"source_idx": 674,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6196,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1921
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000675",
"normalized_example_id": "ex_000675",
"source_idx": 675,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3202,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2562
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000675",
"normalized_example_id": "ex_000675",
"source_idx": 675,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3202,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3202
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000675",
"normalized_example_id": "ex_000675",
"source_idx": 675,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3202,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 2344
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000676",
"normalized_example_id": "ex_000676",
"source_idx": 676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3906,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 3125
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000676",
"normalized_example_id": "ex_000676",
"source_idx": 676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3906,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "B",
"budget": 3906
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000676",
"normalized_example_id": "ex_000676",
"source_idx": 676,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3906,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12960000",
"budget": 2392
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000683",
"normalized_example_id": "ex_000683",
"source_idx": 683,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3986,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12960000",
"budget": 3189
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000683",
"normalized_example_id": "ex_000683",
"source_idx": 683,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3986,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "12960000",
"budget": 3986
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000683",
"normalized_example_id": "ex_000683",
"source_idx": 683,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3986,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 800
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000685",
"normalized_example_id": "ex_000685",
"source_idx": 685,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1334,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1067
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000685",
"normalized_example_id": "ex_000685",
"source_idx": 685,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1334,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1334
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000685",
"normalized_example_id": "ex_000685",
"source_idx": 685,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 1334,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25.5",
"budget": 3793
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000686",
"normalized_example_id": "ex_000686",
"source_idx": 686,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6322,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25.5",
"budget": 5058
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000686",
"normalized_example_id": "ex_000686",
"source_idx": 686,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6322,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "25.5",
"budget": 6322
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000686",
"normalized_example_id": "ex_000686",
"source_idx": 686,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6322,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "r",
"budget": 4733
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000689",
"normalized_example_id": "ex_000689",
"source_idx": 689,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7889,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "r",
"budget": 6311
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000689",
"normalized_example_id": "ex_000689",
"source_idx": 689,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7889,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "r",
"budget": 7889
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000689",
"normalized_example_id": "ex_000689",
"source_idx": 689,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7889,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5\\sqrt{3}}{2}-2",
"budget": 3308
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000691",
"normalized_example_id": "ex_000691",
"source_idx": 691,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5514,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5\\sqrt{3}}{2}-2",
"budget": 4411
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000691",
"normalized_example_id": "ex_000691",
"source_idx": 691,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5514,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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{5\\sqrt{3}}{2}-2",
"budget": 5514
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000691",
"normalized_example_id": "ex_000691",
"source_idx": 691,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 5514,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 5269
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000693",
"normalized_example_id": "ex_000693",
"source_idx": 693,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8782,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 7026
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000693",
"normalized_example_id": "ex_000693",
"source_idx": 693,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8782,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 8782
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000693",
"normalized_example_id": "ex_000693",
"source_idx": 693,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8782,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a",
"budget": 2526
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000696",
"normalized_example_id": "ex_000696",
"source_idx": 696,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4210,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a",
"budget": 3368
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000696",
"normalized_example_id": "ex_000696",
"source_idx": 696,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4210,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "a",
"budget": 4210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000696",
"normalized_example_id": "ex_000696",
"source_idx": 696,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4210,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7960",
"budget": 5356
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000699",
"normalized_example_id": "ex_000699",
"source_idx": 699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8926,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7960",
"budget": 7141
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000699",
"normalized_example_id": "ex_000699",
"source_idx": 699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8926,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "7960",
"budget": 8926
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000699",
"normalized_example_id": "ex_000699",
"source_idx": 699,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 8926,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 1932
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000700",
"normalized_example_id": "ex_000700",
"source_idx": 700,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3220,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 2576
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000700",
"normalized_example_id": "ex_000700",
"source_idx": 700,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3220,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "50",
"budget": 3220
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000700",
"normalized_example_id": "ex_000700",
"source_idx": 700,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3220,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3704
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000701",
"normalized_example_id": "ex_000701",
"source_idx": 701,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6173,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4938
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000701",
"normalized_example_id": "ex_000701",
"source_idx": 701,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6173,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 6173
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000701",
"normalized_example_id": "ex_000701",
"source_idx": 701,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 6173,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1653",
"budget": 1672
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000702",
"normalized_example_id": "ex_000702",
"source_idx": 702,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2787,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1653",
"budget": 2230
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000702",
"normalized_example_id": "ex_000702",
"source_idx": 702,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2787,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "1653",
"budget": 2787
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000702",
"normalized_example_id": "ex_000702",
"source_idx": 702,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2787,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2783
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000703",
"normalized_example_id": "ex_000703",
"source_idx": 703,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4639,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 3711
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000703",
"normalized_example_id": "ex_000703",
"source_idx": 703,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4639,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 4639
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000703",
"normalized_example_id": "ex_000703",
"source_idx": 703,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 4639,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1or2",
"budget": 4663
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000704",
"normalized_example_id": "ex_000704",
"source_idx": 704,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7771,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1or2",
"budget": 6217
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000704",
"normalized_example_id": "ex_000704",
"source_idx": 704,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7771,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-1or2",
"budget": 7771
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000704",
"normalized_example_id": "ex_000704",
"source_idx": 704,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7771,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=x_{2}=\\cdots=x_{n}=1",
"budget": 4588
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000707",
"normalized_example_id": "ex_000707",
"source_idx": 707,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7647,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=x_{2}=\\cdots=x_{n}=1",
"budget": 6118
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000707",
"normalized_example_id": "ex_000707",
"source_idx": 707,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7647,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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}=x_{2}=\\cdots=x_{n}=1",
"budget": 7647
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000707",
"normalized_example_id": "ex_000707",
"source_idx": 707,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 7647,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "400",
"budget": 2397
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000708",
"normalized_example_id": "ex_000708",
"source_idx": 708,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3995,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "400",
"budget": 3196
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000708",
"normalized_example_id": "ex_000708",
"source_idx": 708,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3995,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "400",
"budget": 3995
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000708",
"normalized_example_id": "ex_000708",
"source_idx": 708,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3995,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{3}{2}",
"budget": 1658
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000709",
"normalized_example_id": "ex_000709",
"source_idx": 709,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2763,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{3}{2}",
"budget": 2210
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000709",
"normalized_example_id": "ex_000709",
"source_idx": 709,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2763,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step and the remaining token budget (as a percentage). On the first turn you receive the question instead. Considering the reasoner's current pro... | {
"answer": "-\\frac{3}{2}",
"budget": 2763
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000709",
"normalized_example_id": "ex_000709",
"source_idx": 709,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 2763,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 1880
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000712",
"normalized_example_id": "ex_000712",
"source_idx": 712,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3133,
"... |
[
{
"role": "system",
"content": "You are a reasoning control agent that guides a step-by-step mathematical reasoner.\n\nEach turn you receive the reasoner's latest step 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": 2506
} | {
"data_type": "full_prompt_per_prompt_calibrated_budget",
"source_example_id": "ex_000712",
"normalized_example_id": "ex_000712",
"source_idx": 712,
"augmentation": "online_rl_full_prompt_per_prompt_calibrated_budget",
"budget_source": "per_prompt_calibrated_length_ratios",
"calibrated_length": 3133,
"... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.