{
  "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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.19902",
  "author_total": 3,
  "authors": [
    {
      "name": "Sanyam Jain"
    },
    {
      "name": "Felix Simon Reimers"
    },
    {
      "name": "Stefano Nichele"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4v1c8z1ycgsd8.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.19902",
  "fulltext_url": null,
  "id": "4v1c8z1ycgsd8",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.19902",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "cs.NE"
    ],
    [
      "arxiv",
      "q-bio.PE"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2609.19902",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-17",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4v1c8z1ycgsd8.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:22:24Z",
      "native_id": "2609.19902",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.19902"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.PE",
      "subfield": "evolutionary-biology"
    }
  ],
  "title": "Self-Replicating Neural Cellular Automata: Quantifying Emergent Phenotypic and Genotypic Diversity in an OpenEnded Substrate",
  "title_text": "Self-Replicating Neural Cellular Automata: Quantifying Emergent Phenotypic and Genotypic Diversity in an OpenEnded Substrate",
  "type": "preprint",
  "updated_at": "2026-10-30T12:22:24Z",
  "url": "https://research.draconitic.com/paper/4v1c8z1ycgsd8",
  "venue": "arXiv",
  "versions": []
}