đŸĻĢ Groundhog ¡ fork replay viewer

Share the world, resample the consequences.

Branching agent RL re-runs the same prefix many times to compare actions. Your sandbox rolls back state; nothing rolls back the world — so each branch gets its own clock, its own search ranking, its own latency spike, and those independent draws land straight in the advantage estimate as variance.

Groundhog records the exogenous channels once and serves every branch of a fork the same exogenous noise, while re-rendering anything the branch actually changed. The table below aligns two branches' reads by logical address and marks each one shared, legitimately diverged, or — under full replay — a lie.

Try this: leave deep vs verify selected and switch the condition from (C) Groundhog to (B) Full-replay. Watch GET /review turn red. That single stale read is why (B) converges to the wrong policy while reporting the lowest variance of all three conditions.