{"ID":23475125,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19902","arxiv_id":"2609.19902","title":"Self-Replicating Neural Cellular Automata: Quantifying Emergent Phenotypic and Genotypic Diversity in an OpenEnded Substrate","abstract":"We study an in-silico substrate in which every pixel of a two-channel cellular-automata grid carries a tiny neural network (an agent) that senses its Moore neighborhood. A cell persists only by self-replication: a living neighbor is cloned and its weights are mutated by a uniform perturbation, so that phenotype (cell state) is driven entirely by genotype (network weights). From a handful of seeded founders the system grows into a spatially organized ecosystem of coexisting, competing and dominating species. Our main contribution is a battery of coarse-grained diversity metrics that make such growth measurable at two scales: four phenotypic tools based on cellular-type frequency, entropy and cell variance, and two genotypic tools that colour each agent by a hash of its full weight vector versus a sparse random-weight probe. Across a five-fold sweep of 1680 small runs and 24 long (1000-generation, 200 x 200) runs, the substrate is persistent and self-maintaining in 20 of the 24 long configurations and exposes a clear phenotype-genotype diversity trade-off: raising phenotypic diversity collapses genotypic diversity and vice versa. Full-genome hash colouring further reveals lineage structure that a random-weight probe systematically misses. Code, data and animations are released as supplementary material.","short_abstract":"We study an in-silico substrate in which every pixel of a two-channel cellular-automata grid carries a tiny neural network (an agent) that senses its Moore neighborhood. A cell persists only by self-replication: a living neighbor is cloned and its weights are mutated by a uniform perturbation, so that phenotype (cell s...","url_abs":"https://arxiv.org/abs/2609.19902","url_pdf":"https://arxiv.org/pdf/2609.19902v1","authors":"[\"Sanyam Jain\",\"Felix Simon Reimers\",\"Stefano Nichele\"]","published":"2026-09-17T08:46:26Z","proceeding":"q-bio.PE","tasks":"[\"q-bio.PE\",\"cs.LG\",\"cs.NE\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}