ProCreations/repro-contextual-rollout-bandits-for-reinforcement-learning-with-verifiable-rewards

auto re-queue after judge parked on repeated transport error

Audit FormulaCode historical task-count scope

Audit FormulaCode dataset scale and protect matrix claims

Re-queue: judge parked this logbook after 3x 504 from the backend

Publish source-native max-quality FormulaCode reproduction for WArbqRUsAe

Reserve private paused scoring target

initial commit