* 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
* Add score_answer method to word_ladder
* add unit test for WordLadderDataset::score_answer()
---------
Co-authored-by: Andreas Koepf <andreas.koepf@provisio.com>
- Added extensive test coverage for word ladder configuration validation
- Implemented tests for neighbor computation, path finding, and graph caching
- Included performance and edge case tests
- Verified solution optimality and path generation logic
- Added tests for word set loading and pair generation
