Temporal causal models encode Linear Bounded Automata for context-sensitive languages and become Turing complete with countably infinite variables.
Mooij , Joris M J
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Non-parametric identification and kernel estimation of the drift in time-homogeneous causal diffusions from steady-state observations under known acyclic graph and non-explosion.
Observable Neural ODEs link control-theoretic observability to causal identifiability for continuous-time treatment effect forecasting.
citing papers explorer
-
Temporal Causal Models as a Model of Computation
Temporal causal models encode Linear Bounded Automata for context-sensitive languages and become Turing complete with countably infinite variables.
-
Non-parametric recovery of causal diffusion mechanisms from steady-state observations
Non-parametric identification and kernel estimation of the drift in time-homogeneous causal diffusions from steady-state observations under known acyclic graph and non-explosion.
-
Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time
Observable Neural ODEs link control-theoretic observability to causal identifiability for continuous-time treatment effect forecasting.