open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-05-01 17:45:24 +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

8
tests/test_decimal_chain_sum.py
View file

@ -242,11 +242,11 @@ def test_decimal_precision_scoring():
assert dataset.score_answer("0.3", {"answer": "0.300"}) == 1.0
# Test incorrect answers
assert dataset.score_answer("1.200000001", {"answer": "1.200"}) == 0.01
assert dataset.score_answer("1.199999999", {"answer": "1.200"}) == 0.01
assert dataset.score_answer("1.200000001", {"answer": "1.200"}) == 0.0
assert dataset.score_answer("1.199999999", {"answer": "1.200"}) == 0.0
# Test invalid inputs
assert dataset.score_answer(None, {"answer": "1.200"}) == 0.0
assert dataset.score_answer("", {"answer": "1.200"}) == 0.0
assert dataset.score_answer("invalid", {"answer": "1.200"}) == 0.01
assert dataset.score_answer("1.2.3", {"answer": "1.200"}) == 0.01
assert dataset.score_answer("invalid", {"answer": "1.200"}) == 0.0
assert dataset.score_answer("1.2.3", {"answer": "1.200"}) == 0.0