Ordinal Partition Network (OPN)

Method to discretize continuous time series for EI computation by ranking sub-series.

Neighborhood — ranked by edge-count

concept

Effective Information (EI)
implements
Core measure of causal effect in Hoel's theory; mutual information between uniform input and output distributions.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Deep belief network (DBN)method0.697
Deep architecture with recurrent connections within layers, can learn compressed representations and retain stable attractors.
ordinal scaleconcept0.696
Scale representing ordered attribute values.
Representation Network (RN)framework0.692
Novel construct introduced by this paper: a hypothetical graph embedded in the time series of LLM representations, where each dimension is a node and latent connections are edges.
Comfortable ordinarinessconcept0.683
The quality of being rough, not manicured, concept-free, and genuine, which produces life in everyday situations and modern artifacts.
network of sequencesconcept0.679
The interdependence of morphogenetic sequences, where each triggers others to repair the whole environment, analogous to arithmetic operations.
Orthonormal Basis Vectorsconcept0.669
The set of mutually orthogonal unit vectors that span the concept cone, each independently causally mediating target behavior
Out-of-Distribution (OOD) Generalizationconcept0.669
Machine learning generalization when training and test distributions differ; linked to causal invariance.
Organised structure of relationships between parts, sufficient to exhibit information integration and collective action, can be produced via fully-distributed unsupervised learning.claim0.664
Central claim from connectionist models: complex coordination emerges without centralized control or external teacher.