Lotka Volterra Dynamics

Population dynamics model used by Power to simulate ecological communities with competitive interactions representing puzzle constraints

Neighborhood — ranked by edge-count

method

Power (2019) Sudoku Ecosystem Model
implements
Model where species interactions encode Sudoku constraints and individual-level selection on interaction traits evolves solutions to the puzzle

framework

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.

Information Dynamicsframework0.716
Proposed theoretical framework combining qualitative and quantitative aspects of information, with explicit treatment of processes and information flow; central organizing concept for the paper.
Representational dynamicsconcept0.709
The evolution of an agent's latent representations over the course of training, shown to align with reward improvement when causal emergence is high.
Self Modeling Dynamical Systemsframework0.698
"Plinko" model of high-dimensional dynamicsframework0.695
The paper's illustrative model: closely-spaced trajectories scatter unpredictably off weakly-unstable saddle sets en route to equilibrium.
Self Modelling Dynamical Systemframework0.693
Evolutionary dynamicsconcept0.692
The change in genotype/phenotype frequencies over generations under selection, mutation, and development.
Dynamic Steeringframework0.692
Steering variants that adaptively modulate steering strength based on input context or token position, addressing when to steer
Glauber dynamicsconcept0.687
Stochastic update rule for spin systems; referenced for transformer training dynamics