open-thought/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2026-04-24 17:05:03 +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

14
tests/test_simple_integration.py
View file

@ -94,16 +94,16 @@ def test_score_answer_cases():
("x**2", {"variable": "x", "integrand": "2*x"}, 1.0),
("log(x)", {"variable": "x", "integrand": "1/x"}, 1.0),
# Incorrect but properly formatted
("x**3 + C", {"variable": "x", "integrand": "2*x"}, 0.05),
("cos(X)", {"variable": "X", "integrand": "sin(X)"}, 0.05),
("x**3 + C", {"variable": "x", "integrand": "2*x"}, 0.0),
("cos(X)", {"variable": "X", "integrand": "sin(X)"}, 0.0),
# Malformed expressions
("x**2 +", {"variable": "x", "integrand": "2*x"}, 0.01),
("sin(x", {"variable": "x", "integrand": "cos(x)"}, 0.01),
("x**2 +", {"variable": "x", "integrand": "2*x"}, 0.0),
("sin(x", {"variable": "x", "integrand": "cos(x)"}, 0.0),
# Empty answer
("", {"variable": "x", "integrand": "2*x"}, 0.01),
("", {"variable": "x", "integrand": "2*x"}, 0.0),
# Case sensitivity
("x**2 + C", {"variable": "X", "integrand": "2*X"}, 0.05),
("X**2 + C", {"variable": "x", "integrand": "2*x"}, 0.05),
("x**2 + C", {"variable": "X", "integrand": "2*X"}, 0.0),
("X**2 + C", {"variable": "x", "integrand": "2*x"}, 0.0),
# Alternative constant notation
("x**2 + K", {"variable": "x", "integrand": "2*x"}, 1.0),
("sin(x) + D", {"variable": "x", "integrand": "cos(x)"}, 1.0),