[exit]

schemes exist for cryptographically verifying that an output is the deterministic result of some program run on some input.

i'm at least aware of BitVM * as one example of this.

i wonder whether such schemes could be used to prove that a post is the deterministic function of an open model's inference run.

* https://bitvm.org/ "A prover makes a claim that a given function evaluates for some particular inputs to some specific output. If that claim is false, anyone can perform a fraud proof and punish the prover."

[MattPalmer1086]

Seems like that is possible now. For example [1] "Zero-Knowledge Proof Based Verifiable Inference of Models"

[1] https://arxiv.org/html/2511.19902v1