| Evolutionary models relate genotype and phenotype descriptions or model selection across several levels. | Vanchurin, Geometric framework for biological evolution (2026); Warrell et al., Variational methods for Learning Multilevel Genetic Algorithms using the Kantorovich Monad (2024). | SS-0, SS-2, CC-A19SS-1, CC-A19SS-2. | Provides comparisons for making the represented objects and their connecting relations explicit. | Adapt. These are subject-specific mathematical constructions; the source-set declaration rules here are an FPF adaptation. |
| MOUR-QD distinguishes candidate solutions, feature descriptions, objective values and an archive with local Pareto comparisons. | Janmohamed and Cully, Multi-Objective Quality-Diversity in Unstructured and Unbounded Spaces (2025), Introduction and §2. | SS-1, SS-3, CC-A19SS-3, CC-A19SS-4, worked cases 5.1 and 5.2. | Keeps the source members, space uses and source-to-outcome relation distinguishable. | Adopt/Adapt. Preserve the subject distinctions; express the needed references and relations under FPF. |
| Feature spaces may be learned or unstructured, while uncertain QD may require distributions of fitness and descriptor values rather than single deterministic values. | Janmohamed and Cully (2025), Introduction and §2; Flageat et al., Extract-QD Framework: A Generic Approach for Quality-Diversity in Noisy, Stochastic or Uncertain Domains (2025), Introduction and §2.2. | SS-4, SS-5, CC-A19SS-5, CC-A19SS-6. | Makes the applicable uncertainty and model limits explicit without prescribing one metric or transition model for every use. | Adopt/Adapt. Retain the stated qualifications; select additional models and references for the receiving use. |