{
  "abstract": "Most “agent” architectures begin with a running model and ask how to give it memory, personality, tools, and autonomy. That order makes identity dependent on continuous inference and encourages systems to confuse temporary computation with the person, institution, or character being represented. The Actor–Agent Runtime reverses the order. An Actor is a durable, versioned identity and state capsule that exists when no model is running. An Agent Process is a temporary, bounded computation that wakes because the actor is relevant, receives only permitted knowledge, proposes a reaction or plan, and returns a structured World Patch. Deterministic validators check feasibility, knowledge, authority, resource, identity, and policy constraints before any accepted state change increments the actor revision. The architecture supports persistent people, organizations, game citizens, social proxies, and institutional actors without pretending that thousands of entities are continuously thinking through an LLM. It enables multiplex inference, bounded autonomy, explainable background plans, local-model substitution, replay, and identity continuity. The source model was developed for the game MAIN CHARACTER, but the distinction generalizes to any system in which a durable person-shaped or institution-shaped state must outlive an inference call.",
  "author": "Hayden Lindley",
  "category": "Agents & Simulation",
  "claims": {
    "claims": [
      {
        "claim_id": "P06-C01",
        "evidence_refs": [
          "P06-S01",
          "P06-S02"
        ],
        "limitations": [
          "Integrated production implementation has not been independently receipted."
        ],
        "public": true,
        "scope": "MAIN CHARACTER and generalized runtime.",
        "statement": "Persistent Actor Capsules and temporary Agent Processes can be represented as separate versioned runtime objects joined by validated World Patches.",
        "status": "SPECIFIED"
      },
      {
        "claim_id": "P06-C02",
        "evidence_refs": [
          "P06-S01"
        ],
        "limitations": [
          "Cost improvement depends on workload and implementation."
        ],
        "public": true,
        "scope": "Scheduler design and browser demo potential.",
        "statement": "Deterministic eligibility and cooldown allow many actors to persist without continuous LLM inference.",
        "status": "VERIFIED_MECHANISM"
      },
      {
        "claim_id": "P06-C03",
        "evidence_refs": [
          "P06-S01",
          "P06-S03"
        ],
        "limitations": [
          "No accepted longitudinal comparative run is published."
        ],
        "public": true,
        "scope": "Matched simulation benchmark.",
        "statement": "Actor–Agent separation improves long-duration identity coherence and reduces epistemic leakage compared with conventional chat agents.",
        "status": "HYPOTHESIS"
      }
    ],
    "disclosure_note": "Claims marked non-public in the authored ledger are omitted from this public artifact.",
    "paper": "p06-actor-before-agent",
    "version": "0.1.0",
    "withheld_claim_count": 0
  },
  "date": "2026-07-27",
  "diagrams": {
    "diagrams": [
      {
        "brief": "Persistent Actor Capsule remains across time while short-lived reactive, planning, relationship, and memory processes attach and disappear.",
        "format": "svg",
        "id": "P06-F01",
        "path": "/diagrams/p06-actor-before-agent/P06-F01.svg",
        "status": "source-generated conceptual architecture",
        "title": "Actor before agent"
      },
      {
        "brief": "Dormant → Eligible → Selected → Active → Committed → Cooldown, with deterministic eligibility inputs.",
        "format": "svg",
        "id": "P06-F02",
        "path": "/diagrams/p06-actor-before-agent/P06-F02.svg",
        "status": "source-generated conceptual architecture",
        "title": "Actor lifecycle"
      },
      {
        "brief": "Agent proposal enters revision, knowledge, feasibility, authority, identity, and conflict validators before actor/world events are appended.",
        "format": "svg",
        "id": "P06-F03",
        "path": "/diagrams/p06-actor-before-agent/P06-F03.svg",
        "status": "source-generated conceptual architecture",
        "title": "World Patch validation"
      },
      {
        "brief": "One shared situation feeds bounded actor slots and produces separately validated patches.",
        "format": "svg",
        "id": "P06-F04",
        "path": "/diagrams/p06-actor-before-agent/P06-F04.svg",
        "status": "source-generated conceptual architecture",
        "title": "Multiplex World Pass"
      }
    ],
    "paper": "p06-actor-before-agent"
  },
  "evidence_state": "SPECIFIED",
  "id": "p06-actor-before-agent",
  "institution": "Glyphd Labs",
  "integrity": {
    "claim_ledger_sha256": "1372fcdb21f51e1d1f27fcef1a63441409c8a6429a8d62eee22310f0a84fa512",
    "paper_mdx_sha256": "ccebef81b5adca0e22751e5447404376702ae618ebe9c7e6ce147fbd345a0529"
  },
  "public_disclosure_boundary": "This paper publishes the public-safe runtime distinction and generalized state contracts. It excludes private character canon, unreleased game narrative, real-person proxy data, proprietary scheduling weights, and confidential implementation details. No claim is made that a production-scale city simulation has been completed.",
  "publication_class": "public-safe working paper",
  "publication_url": "https://www.glyphd.com/papers/p06-actor-before-agent",
  "revisions": {
    "paper": "p06-actor-before-agent",
    "revisions": [
      {
        "date": "2026-07-27",
        "summary": "First synthesized public-safe institute edition compiled from the Glyphd project corpus.",
        "version": "0.1.0"
      }
    ]
  },
  "schema_version": "1.0.0",
  "slug": "p06-actor-before-agent",
  "sources": {
    "notes": "Internal source paths are provenance references. Public publication must expose only approved public-safe excerpts or archived public artifacts.",
    "paper": "p06-actor-before-agent",
    "sources": [
      {
        "date": "2026-07-27",
        "id": "P06-S01",
        "path": "01_ACTOR_AGENT_MODEL.md",
        "title": "Actor–Agent Model"
      },
      {
        "date": "2026-07-26/27",
        "id": "P06-S02",
        "path": "Main Character project folder",
        "title": "MAIN CHARACTER system specification corpus"
      },
      {
        "date": "2026-07-24",
        "id": "P06-S03",
        "path": "How_we_can_make_CAS_lightning_fast_for_any_LLM_by_design_or_adaptation.docx",
        "title": "GlyphCAS Design Report"
      },
      {
        "date": "2026-07-25",
        "id": "P06-S04",
        "path": "MCE-1-SYSTEM-CONTRACT-v0.1.md",
        "title": "MCE-1 System Contract"
      }
    ],
    "version": "0.1.0"
  },
  "subtitle": "Persistent identities, temporary inference, and evidence-bound World Patches",
  "title": "Actor Before Agent",
  "version": "0.1.0"
}