פורטביליות סמנטית, דיאלקטים פרטיים: חידוש והעברה שלילית בתקשורת סמויה בין תאי דגימת שפה

תקציר מקורי באנגליתarXiv:2609.11365v1 Announce Type: cross Abstract: 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 packet language, where strict zero-shot transfer fails, and whether inherited interface state helps or harms later learning. First, a leakage-controlled causal interoperability audit over all 30 ordered pairs of six independently trained restricted societies -- under sealed held-out structure and a preregistered raw/orthogonal/linear/nonlinear alignment ladder -- shows the six semantically similar interfaces do not form one raw