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
1336 commits 21 branches 5 tags 37 MiB
Commit graph

39 commits

Author SHA1 Message Date
Ritvik Rastogi
49b07130b3
feat: add scoring cascade for reducing false negatives (#526) 
* feat: add scoring cascade for reducing false negatives in answer verification

* style: fix black and isort formatting

Run black and isort to satisfy pre-commit checks.

Made-with: Cursor

* docs: add scoring cascade example to Quickstart section

Mention the experimental scoring cascade feature at the end of the
Quickstart section with a disclaimer and complete usage examples
showing both the dataset method and standalone function.

Made-with: Cursor

* docs: shorten scoring cascade section in README

Trim to a concise standalone example per review feedback.

Made-with: Cursor

* docs: simplify scoring cascade description in README

Made-with: Cursor

* update readme

---------

Co-authored-by: Zafir Stojanovski <zaf.stojano@gmail.com>
 2026-04-17 21:39:15 +02:00
Zafir Stojanovski
2f9eaee32a
fix: Register missing coin_flip (#507) 
* register missing coin_flip

* lint
 2025-09-15 14:23:30 +02:00
rasdani
72e45e9401
Feat: expose score_answer function without needing to instantiate a dataset (#422) 
* feat: get `score_answer` for a given dataset

* fix: `self` error

* add test
 2025-04-18 10:36:44 +02:00
Andreas Köpf
7853263650
bump dev version to 0.1.19 2025-04-03 22:19:07 +01:00
Andreas Koepf
f25820a0c7 bump version 2025-03-16 15:54:03 +01:00
Andreas Koepf
8c12fe86e2 bump version 2025-03-14 16:21:34 +01:00
Andreas Koepf
1b004bf888 bump version 2025-03-10 00:32:57 +01:00
Andreas Koepf
fb06038e88 update gallery 2025-03-07 16:24:47 +01:00
Andreas Koepf
862617b7e0 update gallery, pypi release, bump version 2025-03-05 23:45:45 +01:00
Andreas Koepf
72233fc2ea bump version, pypi release of 0.1.12 2025-02-26 18:25:16 +01:00
Andreas Koepf
b5f6f7d753 bump version, update gallery 2025-02-23 22:36:39 +01:00
Andreas Koepf
e4102a44f6 dev minor version one ahead of PyPI released version 2025-02-22 16:54:05 +01:00
Andreas Köpf
700aab6114
Merge pull request #180 from Adefioye/list-functions 
Add induction-based tasks for list functions
 2025-02-21 16:20:49 +01:00
abdulhakeem
624594bb1a Commit more changes 2025-02-21 00:37:29 -06:00
Andreas Koepf
f1daa8d1da update GALLERY.my, bump version 2025-02-20 23:03:54 +01:00
Andreas Koepf
f7e928711e bump version, update GALLERY.md 2025-02-14 23:34:59 +01:00
Andreas Koepf
56ba500959 update GALLERY.md & bump version 2025-02-11 23:43:56 +01:00
Andreas Koepf
1f9d9d27ab bump version 2025-02-09 00:39:48 +01:00
joesharratt1229
184d5b4270 registered rearc 2025-02-08 11:42:49 +00:00
Andreas Koepf
ff74dfb5f2 fix tool.hatch.build section in pyproject.toml 2025-02-07 19:02:43 +01:00
Andreas Koepf
d3752a0d76 bump version to 0.1.14 2025-02-07 18:28:06 +01:00
Rich Jones
7274f79c50 precommit hook linting 2025-02-03 14:40:58 +01:00
Rich Jones
0c9094e9f4 adds zebrapuzzles 2025-02-03 14:34:57 +01:00
Andreas Koepf
9a1270dd95 add arc_1d dataset 2025-02-02 23:03:56 +01:00
Andreas Koepf
bb620a1066 fix main __init__.py 2025-02-01 17:06:03 +01:00
Andreas Koepf
2775046748 update dataset gallery 2025-02-01 17:04:18 +01:00
Andreas Koepf
cc0312e446 add first example with OpenRLHF 2025-01-28 14:40:06 +00:00
Andreas Koepf
0dcff77b37 add reasoning_gym.create_dataset({name}, ...) global factory function 2025-01-25 00:58:34 +01:00
Andreas Koepf
3dc80be7d2 formatting, cleanup 2025-01-24 17:12:42 +01:00
Andreas Koepf (aider)
e6e8f8cc42 refactor: Rename relationships module to graphs 2025-01-24 16:50:12 +01:00
Andreas Koepf (aider)
b6f673aa54 feat: Add family relationships dataset with configurable family trees 2025-01-24 16:46:43 +01:00
Andreas Koepf (aider)
b66b1c09b9 feat: Add SimpleEquationsDataset to algebra module 
Developed together with Benjamin Rio (benjamrio)
 2025-01-24 16:08:05 +01:00
Andreas Koepf
20069b2a7d formatting 2025-01-24 10:34:07 +01:00
Andreas Koepf (aider)
c4b0923157 feat: Add Sudoku puzzle generator with configurable difficulty 2025-01-23 22:55:09 +01:00
Andreas Koepf (aider)
703fcda3cd feat: Add algorithmic and data modules to reasoning_gym package 2025-01-23 19:21:57 +01:00
Andreas Koepf (aider)
d0444f3546 feat: Add logic module to reasoning_gym package imports 2025-01-23 14:41:44 +01:00
Andreas Koepf (aider)
e1d04f8a2f feat: Add cognition module with initial reasoning tasks namespace 2025-01-23 13:31:30 +01:00
Andreas Koepf (aider)
e9e90051d6 feat: Expose arithmetic modules automatically in reasoning_gym package 2025-01-23 12:25:26 +01:00
Andreas Koepf (aider)
3f80fd7b80 build: Initialize reasoning_gym package structure with packaging and development setup 2025-01-23 10:50:54 +01:00