-
Update README.md
-
Add rubric_as_reward_think_step90
-
Add rubric_as_reward_think_step60
-
Add twr_self_only_step60
-
Remove golden_only step70 (keep only 60/90)
-
Add twr_golden_only_step70
-
Add twr_golden_only_step60
-
Add twr_mixed_step80
-
Add twr_mixed_step70
-
Add twr_mixed_step60
-
Add README (model↔paper mapping + links to code/data repos)
-
Add rubric_verifier
-
Add twr_sft_warmup
-
Add twr_self_only_step90
-
Add twr_golden_only_step90
-
Add twr_mixed_step90
-
initial commit