{"id":"oscr:b:ZT9RYNQRTEMFC-C","url":"https://openscicode.org/b/oscr:b:ZT9RYNQRTEMFC-C","status":"current","doi":"10.1038/s44387-026-00109-y","since":"2026-11-14","page":"doi_10.1038_s44387-026-00109-y","repo":"github.com/diegomac17/sparrow-pd","commit":"e3c196b5a0cd905dfd04db7874cb2ba5301600aa","path":"sparrow.py","swhid":"swh:1:cnt:f38bb16ef38b703960bd72763869ff31d53afc48","lines":[353,437],"symbol":"SparrowModel.run_rl","paragraphs":[[61,"Methods › Model training"],[49,"Methods › Reinforcement learning for fine-tuning"]],"method":"lexical-v1","origin":"machine","paper":"https://doi.org/10.1038/s44387-026-00109-y","swhid_qualified":"swh:1:cnt:f38bb16ef38b703960bd72763869ff31d53afc48;origin=https://github.com/diegomac17/sparrow-pd;anchor=swh:1:rev:e3c196b5a0cd905dfd04db7874cb2ba5301600aa;path=/sparrow.py;lines=353-437","reader":"https://openscicode.org/paper/doi_10.1038_s44387-026-00109-y/?path=sparrow.py#L353-L437","citation":"Code block oscr:b:ZT9RYNQRTEMFC-C (https://openscicode.org/b/oscr:b:ZT9RYNQRTEMFC-C)\nsparrow.py, lines 353 to 437, in github.com/diegomac17/sparrow-pd (https://github.com/diegomac17/sparrow-pd), commit e3c196b5a0cd905dfd04db7874cb2ba5301600aa.\nPaper: https://doi.org/10.1038/s44387-026-00109-y\nSWHID: swh:1:cnt:f38bb16ef38b703960bd72763869ff31d53afc48;origin=https://github.com/diegomac17/sparrow-pd;anchor=swh:1:rev:e3c196b5a0cd905dfd04db7874cb2ba5301600aa;path=/sparrow.py;lines=353-437"}