Cairn — leave, come back, same world
An explicit world ledger makes video generation return-consistent, and editable.
Video world models forget. Turn the camera away from a chair for a few seconds and turn back, and it is a different chair, somewhere else, or gone. The usual fixes give the model more implicit memory — a longer context window, or a compressed latent. Both decay with how long you looked away.
Cairn takes the world out of the weights. Objects live in an explicit external ledger — persistent id, pose, appearance, provenance — written by perception on the model's own generated frames, and read back to coerce generation when the camera returns. A table lookup costs the same whether you looked away for 4 frames or 400.
Over 5 seeds, at 128 frames away, every baseline returns a broken world 0% of the time and Cairn 100%, with a flat 3.6 cm error. Try to break it below.
cairn package. The first
load takes roughly 30 seconds and is cached afterwards. Nothing is sent to a server — the whole
benchmark runs on your machine.The room, from four directions.
Cairn's entire memory is this table plus its transaction log. It is written by perception running on the generated frames — never from ground truth — and every mutation is invertible, so the world rewinds to any instant.