open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-23 16:55:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Minor question template & score_answer improvements (#261)

Browse source 
* math prompt improvements
* ignore brackets in complex_arithmetic results
* improve additional instruction in prompt of polynomial_equations
* more strict tests for score_answer in polynomial_equations
* simplify special reward handling
* fix test_intermediate_integration
* fix sokoban dataset
* add common dataset score_answer consistency test
This commit is contained in:
Andreas Köpf 2025-03-04 21:55:09 +01:00 • committed by GitHub
parent bf24999bb0
commit b2904ccab9
106 changed files with 403 additions and 507 deletions
Download patch file Download diff file Expand all files Collapse all files

9
tests/test_quantum_lock.py
View file

@ -43,7 +43,8 @@ def test_quantumlock_items():
assert "target_value" in item["metadata"]
# Verify solution works
assert dataset.score_answer(answer=item["metadata"]["solution_path"], entry=item) == 1.0
answer = "".join(item["metadata"]["solution_path"])
assert dataset.score_answer(answer=answer, entry=item) == 1.0
assert dataset.score_answer(answer=None, entry=item) == 0.0
@ -98,17 +99,17 @@ def test_quantumlock_scoring():
dataset = QuantumLockDataset(config)
for item in dataset:
solution = item["metadata"]["solution_path"]
solution = item["answer"]
# Test correct solution
assert dataset.score_answer(solution, item) == 1.0
# Test empty/None answers
assert dataset.score_answer(None, item) == 0.0
assert dataset.score_answer("", item) == 0.1
assert dataset.score_answer("", item) == 0.0
# Test invalid buttons
assert dataset.score_answer("XYZ", item) == 0.1
assert dataset.score_answer("XYZ", item) == 0.0
# Test case insensitivity
if solution: