AIC/BIC Model Selection Criteria

Used as theoretical motivation for UCCT's log k budget term as complexity penalty mirroring model selection

Neighborhood — ranked by edge-count

concept

anchoring strength S
analogous_to
Composite score S = ρd − dr − log k predicting anchoring success.
Logistic success surrogate
analogous_to
Phenomenological fit P(success)=σ(αS+β) used to summarize sharpness and midpoints.

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.

model selectionconcept0.791
Comparing models using log-evidence approximated by free energy.
Bayesian Model Selectionconcept0.759
Choosing among candidate models based on model evidence.
Natural Selection as Bayesian Model Selectionconcept0.729
Analogy between evolution (model selection) and Bayesian model reduction; but evolution is not curious or insightful
ByCS: Bayesian Example Selectionframework0.709
Selection/weighting strategy for ICL demonstrations; in UCCT terms alters context posterior
Friston & Penny (2011) — Post hoc Bayesian model selectionconcept0.706
Source paper for Bayesian model reduction methodology used in structure learning
Autoregressive modelsframework0.700
Second model system studied; used to show why flat autoregressive LLMs struggle with long-range coherence.
Smith & Boyd (1991) criteria are irrelevant across the vast majority of the space of possible agents.claim0.698
Dismissal of earlier criteria as too narrow.
Levels Of Selection Approachframework0.694