Causal-fate dynamics of unrealized influence

Key points

• Many dynamical systems generate influences whose consequences are not fully exhausted in the realized trajectory at the moment they arise.1
• A connectome-constrained Caenorhabditis elegans model first motivates the biological hypothesis that unresolved inter-neuronal influence may persist and contribute to later propagation; it does not establish such a mechanism in living animals.1
• We next examine operational Internet routing, where a dynamically updated cross-observer history retains predictive information beyond the current local route state.1
• We then use the representation to construct a Transformer architecture that explicitly transports and selectively realizes latent contextual influence while retaining language-modeling function.1

Sources (1)

• [1]Causal-fate dynamics of unrealized influence
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 07:48 AM

  Here we formulate causal-fate dynamics, in which generated influence may be realized, remain latent, or be transformed by subsequent dynamics, and give an exact finite-transport representation when the relevant maps are specified.

  Many dynamical systems generate influences whose consequences are not fully exhausted in the realized trajectory at the moment they arise.

Extractive summary: sentences quoted from the sources.