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

include ranges rather than sampled values in difficulty metadata dicts (#387)

Browse source 
* update difficulty metadata for logic datasets

* update difficulty metadata for graph datasets

* update difficulty metadata for geometry datasets

* update difficulty metadata for games datasets

* update difficulty metadata for cognition datasets

* update difficulty metadata for arithmetic datasets

* update difficulty metadata for arc datasets

* update difficulty metadata for algorithmic datasets

* update difficulty metadata for algebra datasets

* use tuples

* update tests

* update tests
This commit is contained in:
Oliver Stanley 2025-03-20 09:27:03 +00:00 • committed by GitHub
parent b69c35818a
commit 7475a20700
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
80 changed files with 304 additions and 126 deletions
Download patch file Download diff file Expand all files Collapse all files

8
reasoning_gym/cognition/needle_haystack.py
View file

@ -103,7 +103,13 @@ class NeedleHaystackDataset(ProceduralDataset):
return {
"question": full_text,
"answer": stack["needle"][0],
"metadata": {"question": question, "difficulty": {"num_statements": num_statements}},
"metadata": {
"question": question,
"num_statements": num_statements,
"difficulty": {
"num_statements": (self.config.min_num_statements, self.config.max_num_statements),
},
},
}
def score_answer(self, answer: Optional[str], entry: dict[str, Any]) -> float: