open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-19 12:58:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: Simplify jug puzzle dataset generation and solution verification

Browse source
This commit is contained in:
Andreas Koepf 2025-02-20 22:38:10 +01:00 • committed by Andreas Koepf (aider)
parent 0f798457ed
commit d7db2ed838
1 changed files with 5 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

11
reasoning_gym/algorithmic/jugs.py
View file

@ -258,8 +258,7 @@ class JugsDataset(ProceduralDataset):
solution = generate_jug_solution(puzzle["jug_capacities"], puzzle["target"])
cap_str = ", ".join(f"{chr(ord('A')+i)}:{cap}" for i, cap in enumerate(puzzle["jug_capacities"]))
question = f"""
You are a police officer. A maniac has planted a bomb next to a public fountain.
question = f"""You are a police officer. A maniac has planted a bomb next to a public fountain.
To defuse the bomb, you must solve a puzzle. The puzzle is solved when you fill any of the available jugs with the target amount of water.
@ -276,7 +275,7 @@ And your target is: {puzzle['target']} litres.
How do you defuse the bomb?
Reply as a JSON-parsable list of moves which result in any of the jugs being filled with the target amount.
"""
"""
return {
"question": question,
@ -297,12 +296,12 @@ Reply as a JSON-parsable list of moves which result in any of the jugs being fil
float: The computed score between 0.0 and 1.0.
"""
if answer == None:
if answer is None:
return 0.0
danswer = json.loads(answer)
try:
valid, states = verify_solution(entry["metadata"]["puzzle"], danswer)
danswer = json.loads(answer)
valid, _ = verify_solution(entry["metadata"]["puzzle"], danswer)
if not valid:
return 0.01
else: