Narcis Marincat

What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization

Restricting what a module can read may improve what a system learns to compute. We test this in a preregistered confirmation with sixty four-cell systems sharing a frozen language-model backbone and communicating through learned continuous packets. Five conditions vary evidence masking, ownership markers, and replaceme...

Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells

In shared-genome language-model societies, restricted evidence visibility favors reusable, value-indexed latent packet interfaces, whereas the sole high-performing globally visible model in the parent study learned an episode-entangled code. This companion study asks whether independently trained societies share one pa...

What You Can’t See Is What You Learn: Restricted Evidence Visibility Favors Compositional Generalization in Shared-Genome Language-Model Societies