Dataset Viewer
Auto-converted to Parquet Duplicate
question
stringlengths
152
158
metadata
stringlengths
160
172
task_source
stringclasses
1 value
formatted_prompt
listlengths
2
2
responses_by_sample
listlengths
1
1
tokens_by_sample
listlengths
1
1
num_rounds_by_sample
listlengths
1
1
continuation_prompts_by_sample
listlengths
1
1
continuation_text_by_sample
listlengths
1
1
strategy_type
stringclasses
1 value
termination_reason_by_sample
listlengths
1
1
correct_round_by_sample
listlengths
1
1
smart_termination_enabled
bool
1 class
retry_count_by_sample
listlengths
1
1
answers_by_sample
listlengths
1
1
evals_by_sample
listlengths
1
1
eval_metadata_by_sample
listlengths
1
1
"Using ALL of the numbers 12, 4, 7, 1, 2, 5, 21, 88, create an expression that equals 109. You must (...TRUNCATED)
"{\"numbers\": [12, 4, 7, 1, 2, 5, 21, 88], \"target\": 109, \"operators_used\": [\"/\", \"+\", \"/\(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 109 using all those numbers: 12, 4, 7, 1, 2, 5(...TRUNCATED)
[ 79571 ]
[ 92 ]
[[" Wait… I’ll continue exploring alternative solution strategies. Let’s try something new. ",(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 109 using all those numbers: 12, 4, 7, 1, 2, 5(...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[[[],["","88 + 21 * (5 - 12 / ((7 - 4) / (2 - 1)))"],["88 + 21 * (5 - 12 / ((7 - 4) / (2 - 1)))","88(...TRUNCATED)
[[[],[false,true],[true,true],[true],[true,true],[true],[true,true],[true,true],[true],[true],[true,(...TRUNCATED)
[[[],[{"answer_block":"","error":"Missing answer block","final_answer":null,"is_correct":false},{"an(...TRUNCATED)
"Using ALL of the numbers 25, 69, 58, 14, 55, 24, 36, 60, create an expression that equals 176. You (...TRUNCATED)
"{\"numbers\": [25, 69, 58, 14, 55, 24, 36, 60], \"target\": 176, \"operators_used\": [\"-\", \"+\",(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 176 using all these numbers: 25, 69, 58, 14, 5(...TRUNCATED)
[ 34705 ]
[ 1 ]
[ [] ]
[["<think>\nOkay, let's try to figure out how to make 176 using all these numbers: 25, 69, 58, 14, 5(...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[ [ [] ] ]
[ [ [] ] ]
[ [ [] ] ]
"Using ALL of the numbers 55, 36, 6, 3, 14, 99, 17, 82, create an expression that equals 245. You mu(...TRUNCATED)
"{\"numbers\": [55, 36, 6, 3, 14, 99, 17, 82], \"target\": 245, \"operators_used\": [\"*\", \"-\", \(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 245 using all these numbers: 55, 36, 6, 3, 14,(...TRUNCATED)
[ 32845 ]
[ 108 ]
[[" Wait… I’ll continue exploring alternative solution strategies. Let’s try something new. ",(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 245 using all these numbers: 55, 36, 6, 3, 14,(...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[[["( (82 * 3) - ( (99 - 55) / ( (36 - 17) - 14 ) ) ) + (6 / 3)"],["82 * 3 - (99 - 55) / (36 - 17 - (...TRUNCATED)
[[[false],[false],[false],[],[false],[false],[false],[false],[],[],[false],[false],[],[false],[],[fa(...TRUNCATED)
[[[{"answer_block":"( (82 * 3) - ( (99 - 55) / ( (36 - 17) - 14 ) ) ) + (6 / 3)","error":"Expression(...TRUNCATED)
"Using ALL of the numbers 87, 87, 29, 2, 19, 4, 1, 1, create an expression that equals 281. You must(...TRUNCATED)
"{\"numbers\": [87, 87, 29, 2, 19, 4, 1, 1], \"target\": 281, \"operators_used\": [\"/\", \"+\", \"/(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 281 using all the numbers 87, 87, 29, 2, 19, 4(...TRUNCATED)
[ 32771 ]
[ 86 ]
[[" Wait… I’ll continue exploring alternative solution strategies. Let’s try something new. ",(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 281 using all the numbers 87, 87, 29, 2, 19, 4(...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[[["87 * (2 + 1 + 1) + 29 - 19 - 4"],["87 * 2 + 87 + 29 + 19 - 4 - 1 - 1","87 * (2 + 1 + 1) + 29 - 1(...TRUNCATED)
[[[false],[false,false],[false,false],[false],[false],[false],[],[false],[],[false],[false],[],[fals(...TRUNCATED)
[[[{"answer_block":"87 * (2 + 1 + 1) + 29 - 19 - 4","error":"Expression does not equal stated result(...TRUNCATED)
"Using ALL of the numbers 56, 63, 7, 50, 44, 1, 87, 52, create an expression that equals 132. You mu(...TRUNCATED)
"{\"numbers\": [56, 63, 7, 50, 44, 1, 87, 52], \"target\": 132, \"operators_used\": [\"-\", \"/\", \(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 132 using all the numbers 56, 63, 7, 50, 44, 1(...TRUNCATED)
[ 32848 ]
[ 204 ]
[[" Wait… I’ll continue exploring alternative solution strategies. Let’s try something new. ",(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 132 using all the numbers 56, 63, 7, 50, 44, 1(...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[[["87 + 52 - 7 + 63 - 50 - 56 + 44 - 1"],["87 + 52 - 7 + 63 - 50 - 56 + 44 - 1"],["87 + 52 - 7 + 63(...TRUNCATED)
[[[true],[true],[true],[true],[true],[true],[true],[true],[true],[true],[true],[true],[true],[true],(...TRUNCATED)
[[[{"answer_block":"87 + 52 - 7 + 63 - 50 - 56 + 44 - 1","error":null,"final_answer":132.0,"is_corre(...TRUNCATED)
"Using ALL of the numbers 7, 1, 49, 7, 28, 59, 3, 44, create an expression that equals 521. You must(...TRUNCATED)
"{\"numbers\": [7, 1, 49, 7, 28, 59, 3, 44], \"target\": 521, \"operators_used\": [\"/\", \"*\", \"/(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's see. I need to make an expression that equals 521 using all the numbers 7, 1(...TRUNCATED)
[ 32770 ]
[ 248 ]
[[" Wait… I’ll continue exploring alternative solution strategies. Let’s try something new. ",(...TRUNCATED)
[["<think>\nOkay, let's see. I need to make an expression that equals 521 using all the numbers 7, 1(...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[[[],[],["59 × 7 + 44 × (3 - 1) + (49 - 28) - (7 ÷ 7)"],["59 * 7 + 44 * (3 - 1) + (49 - 28) - (7 (...TRUNCATED)
[[[],[],[false],[false],[false],[false],[false],[false],[false],[false],[false],[],[false],[false],[(...TRUNCATED)
[[[],[],[{"answer_block":"59 * 7 + 44 * (3 - 1) + (49 - 28) - (7 / 7)","error":"Expression uses an u(...TRUNCATED)
"Using ALL of the numbers 97, 4, 93, 26, 3, 24, 20, 31, create an expression that equals 620. You mu(...TRUNCATED)
"{\"numbers\": [97, 4, 93, 26, 3, 24, 20, 31], \"target\": 620, \"operators_used\": [\"-\", \"/\", \(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 620 using all the numbers 97, 4, 93, 26, 3, 24(...TRUNCATED)
[ 32786 ]
[ 147 ]
[[" Wait… I’ll continue exploring alternative solution strategies. Let’s try something new. ",(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 620 using all the numbers 97, 4, 93, 26, 3, 24(...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[[["(24 * 26) - 4 + (97 - 93) - (31 - 20) + 3"],[],["(24 * 26) - 4 + (97 - 93) - (31 - 20 - 3)"],["((...TRUNCATED)
[[[false],[],[false],[false],[false],[false],[false],[false],[false],[false],[],[],[],[],[],[false],(...TRUNCATED)
[[[{"answer_block":"(24 * 26) - 4 + (97 - 93) - (31 - 20) + 3","error":"Expression does not equal st(...TRUNCATED)
"Using ALL of the numbers 45, 69, 55, 40, 1, 9, 8, 83, create an expression that equals 913. You mus(...TRUNCATED)
"{\"numbers\": [45, 69, 55, 40, 1, 9, 8, 83], \"target\": 913, \"operators_used\": [\"*\", \"+\", \"(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's see. I need to make an expression that equals 913 using all the numbers 45, (...TRUNCATED)
[ 32853 ]
[ 196 ]
[[" Wait… I’ll continue exploring alternative solution strategies. Let’s try something new. ",(...TRUNCATED)
[["<think>\nOkay, let's see. I need to make an expression that equals 913 using all the numbers 45, (...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[[["83 * ((69 - 55) - (45 - 40) + 9 - 8 + 1)"],["","83 * (69 - 55 - 45 + 40 + 9 - 8 + 1)","83 * (69 (...TRUNCATED)
[[[true],[false,true,true,true],[true],[true,true],[true],[true,true],[true],[true,true],[true,true](...TRUNCATED)
[[[{"answer_block":"83 * ((69 - 55) - (45 - 40) + 9 - 8 + 1)","error":null,"final_answer":913.0,"is_(...TRUNCATED)
"Using ALL of the numbers 72, 3, 67, 1, 43, 1, 93, 53, create an expression that equals 145. You mus(...TRUNCATED)
"{\"numbers\": [72, 3, 67, 1, 43, 1, 93, 53], \"target\": 145, \"operators_used\": [\"/\", \"-\", \"(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's see. I need to use all these numbers: 72, 3, 67, 1, 43, 1, 93, 53. Each exac(...TRUNCATED)
[ 33648 ]
[ 61 ]
[[" Wait… I’ll continue exploring alternative solution strategies. Let’s try something new. ",(...TRUNCATED)
[["<think>\nOkay, let's see. I need to use all these numbers: 72, 3, 67, 1, 43, 1, 93, 53. Each exac(...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[[["(93 + 53) - (72 / (67 - 43) + 3 + 1 + 1)"],["93 + 53 - (72 / (67 - 43)) - 3 - 1 - 1"],["93 + 53 (...TRUNCATED)
[[[false],[false],[false],[false],[false],[false],[false],[false],[false],[false],[false],[false],[f(...TRUNCATED)
[[[{"answer_block":"(93 + 53) - (72 / (67 - 43) + 3 + 1 + 1)","error":"Expression does not equal sta(...TRUNCATED)
"Using ALL of the numbers 13, 1, 13, 68, 2, 2, 93, 62, create an expression that equals 102. You mus(...TRUNCATED)
"{\"numbers\": [13, 1, 13, 68, 2, 2, 93, 62], \"target\": 102, \"operators_used\": [\"/\", \"-\", \"(...TRUNCATED)
countdown
[{"content":"You are a helpful assistant that solves math problems by reasoning step-by-step. Show y(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 102 using all these numbers: 13, 1, 13, 68, 2,(...TRUNCATED)
[ 32887 ]
[ 280 ]
[[" Wait… I’ll continue exploring alternative solution strategies. Let’s try something new. ",(...TRUNCATED)
[["<think>\nOkay, let's try to figure out how to make 102 using all these numbers: 13, 1, 13, 68, 2,(...TRUNCATED)
budget_forcing
[ "budget_reached" ]
[ null ]
false
[ 0 ]
[[["68 + (93 - 62) * (13 / 13) + 2 * 2 - 1"],["68 + (93 - 62) * (13 / 13) + 2 * 2 - 1","68 + (93 - 6(...TRUNCATED)
[[[true],[true,true],[true,true],[true,true],[true,true],[true,true],[true,true],[true],[true,true],(...TRUNCATED)
[[[{"answer_block":"68 + (93 - 62) * (13 / 13) + 2 * 2 - 1","error":null,"final_answer":102.0,"is_co(...TRUNCATED)
End of preview. Expand in Data Studio

EAS-Qwen3-4B-Thinking-2507-cd8arg-budget_forcing

Countdown reasoning with budget_forcing strategy to 32768 tokens

Dataset Info

  • Rows: 100
  • Columns: 17

Columns

Column Type Description
question Value('string') The countdown problem statement
metadata Value('string') JSON with target number, available numbers, and solution
task_source Value('string') Task type identifier (countdown)
formatted_prompt List({'content': Value('string'), 'role': Value('string')}) Initial prompt messages sent to the model
responses_by_sample List(List(Value('string'))) Full model response [sample_idx][round_idx] = response string
tokens_by_sample List(Value('int64')) Total token count for each sample (based on continuation_text)
num_rounds_by_sample List(Value('int64')) Number of continuation rounds for each sample
continuation_prompts_by_sample List(List(Value('string'))) Continuation prompts used [sample_idx][round_idx] = prompt string
continuation_text_by_sample List(List(Value('string'))) Truncated text used for continuation [sample_idx][round_idx]. For budget_forcing: truncated at first tag. For other strategies: same as responses_by_sample.
strategy_type Value('string') Prompting strategy: 'iterative', 'budget_forcing', or 'random_noise'
termination_reason_by_sample List(Value('string')) Why each sample terminated: 'max_rounds_reached', 'budget_reached', or 'answer_correct'
correct_round_by_sample List(Value('null')) Round number where correct answer was first found (None if never correct)
smart_termination_enabled Value('bool') Whether smart termination was enabled for this run
retry_count_by_sample List(Value('int64')) Total retry attempts per sample due to empty or too-short responses (0 if no retries needed)
answers_by_sample List(List(List(Value('string')))) Extracted answer spans [sample][round][answer_idx]
evals_by_sample List(List(List(Value('bool')))) Correctness evaluations [sample][round][answer_idx]
eval_metadata_by_sample List(List(List({'answer_block': Value('string'), 'error': Value('string'), 'final_answer': Value('float64'), 'is_correct': Value('bool')}))) Evaluation details [sample][round][answer_idx]

Generation Parameters

{
  "script_name": "stage_01_generate_reasoning.py",
  "model": "hosted_vllm/Qwen/Qwen3-4B-Thinking-2507<api_base>http://10.32.37.18:10080/v1",
  "hyperparameters": {
    "temperature": 0.7,
    "max_tokens_per_round": 32768,
    "target_total_tokens": 32768,
    "samples": 1,
    "strategy": "budget_forcing",
    "max_rounds": null,
    "min_tokens": 10,
    "max_retries_per_round": -1
  },
  "input_datasets": [],
  "description": "Countdown reasoning with budget_forcing strategy to 32768 tokens",
  "experiment": "degen_test_1_countdown",
  "strategy": "budget_forcing",
  "arg_count": 8,
  "seed": 42,
  "smart_termination": false,
  "max_rounds": null,
  "min_tokens": 10,
  "status": "completed",
  "completed_at": "2025-12-25T06:15:19.989623"
}

Experiment Documentation

For complete experiment details, see https://github.com/TAUR-Lab/Reasoning-Horizons/tree/main/experiments/degen_test_1_countdown

Usage

from datasets import load_dataset

dataset = load_dataset("reasoning-degeneration-dev/EAS-Qwen3-4B-Thinking-2507-cd8arg-budget_forcing", split="train")
print(f"Loaded {len(dataset)} rows")

This dataset is tracked in reasoning-degeneration-dev/PROJECT-MANIFEST

Downloads last month
4