Towards Computational Provenance: Carrying Causal-State Evidence in Generated Text
A language model's output does not by itself provide verifiable evidence about the internal computation that produced it. We study computational provenance: whether generated text can carry detectable evidence of which causally relevant internal state occurred. We test a bounded form of this idea in two controlled architectures: a modular feed-forward neural network and a transformer-based model.…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
