P3Mnh7mF5a / pages /methods

Commit History

Repair Claims 1, 4, and 5 with executed finite-state audits
6eca7c5
verified

DineshAI commited on

Update logbook: Repro - Provable Benefits of RLVR over SFT for Reasoning Models
538a3cb
verified

DineshAI commited on