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

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 061282e373
commit 5d7fbac0ad
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
106 changed files with 403 additions and 507 deletions
Download patch file Download diff file Expand all files Collapse all files

12
tests/test_self_reference.py
View file

@ -18,8 +18,8 @@ def test_self_reference():
# Test the scoring
assert dataset.score_answer(answer=item["answer"], entry=item) == 1.0
assert dataset.score_answer(answer=99, entry=item) == 0.1
assert dataset.score_answer(answer="99", entry=item) == 0.1
assert dataset.score_answer(answer=99, entry=item) == 0.0
assert dataset.score_answer(answer="99", entry=item) == 0.0
assert dataset.score_answer(answer=None, entry=item) == 0.0
# # Medium
@ -34,8 +34,8 @@ def test_self_reference():
# Test the scoring
assert dataset.score_answer(answer=item["answer"], entry=item) == 1.0
assert dataset.score_answer(answer=99, entry=item) == 0.1
assert dataset.score_answer(answer="99", entry=item) == 0.1
assert dataset.score_answer(answer=99, entry=item) == 0.0
assert dataset.score_answer(answer="99", entry=item) == 0.0
assert dataset.score_answer(answer=None, entry=item) == 0.0
# # Hard
@ -50,6 +50,6 @@ def test_self_reference():
# Test the scoring
assert dataset.score_answer(answer=item["answer"], entry=item) == 1.0
assert dataset.score_answer(answer=99, entry=item) == 0.1
assert dataset.score_answer(answer="99", entry=item) == 0.1
assert dataset.score_answer(answer=99, entry=item) == 0.0
assert dataset.score_answer(answer="99", entry=item) == 0.0
assert dataset.score_answer(answer=None, entry=item) == 0.0