Version: 1.0 Layer: THREE — RECURSIVE Domains: 5
Passes: 4 Entity Classes: 15 Edge Types: 20
Federation Architecture  ◆  Layer Three  ◆  Root-LD v1.0

Recursive-LD
as Layer Three
of Root-LD

How Recursive-LD functions as the edge and cognitive context layer
within the Root-LD federation — growing more intelligent over time
as entities accumulate relationships, records, and dimensional reasoning data.

Layer Three is the only Root-LD layer not populated at entity ingestion. It is not static. It grows. Every edge added between entities, every dimensional reasoning record written, every telemetry chain anchored — all of it is Layer Three. It is what makes the federation intelligent, not merely indexed.

Spec: Root-LD v1.0
Layer: Three of Three
Domains: 5 Registered
Edge Types: 20
Entity Classes: 15
Root-LD Three-Layer Architecture Structural Context

The Root-LD specification defines three layers of entity structure. Every entity in the federation carries all three. Layer One is the immutable core. Layer Two is the content expression. Layer Three — Recursive-LD — is the edge and intelligence layer that evolves.

L1 Anchor
Anchor-LD
Immutable metadata. The permanent identity record of an entity — URI, type declarations, creation timestamp, federation membership, domain code. Written once. Never modified. The root of the entity graph.
IMMUTABLE
L2 Body
Body-LD
Content and semantic expression. The entity's active properties, descriptions, relationships to external schema vocabularies, and primary structured data blocks. Updated as the entity evolves.
VERSIONED
L3 Recursive
Recursive-LD
Edge and cognitive context layer. Cross-entity relationships, dimensional reasoning records, confidence-scored semantic edges, and cognitive telemetry chains. Not written at ingestion — accumulated over time. The intelligence layer.
ACCUMULATIVE

The helix metaphor is deliberate. A consuming system can enter a Recursive-LD record at any node and spiral outward — following edges upward to broader context or downward into component entities — indefinitely. The graph does not end. It deepens.

Four Federation Passes Intelligence Pipeline

Recursive-LD edges between entities in the federation are written by four sequential passes. Each pass operates at a different level of semantic resolution. The passes are additive — later passes build on earlier ones but do not replace them. Confidence scores are written per-edge and per-pass.

Pass 01
Deterministic
Pass 02
Lexical
Pass 03
Semantic-LLM
Pass 04
Finetuned
01 Deterministic
Pass
Conf: 1.0

Exact-match relationship detection. Writes edges where the relationship between two entities can be established with certainty from structured metadata — shared domain code, explicit parent-child declarations, federation membership links.

Confidence score: 1.0. These edges are treated as ground truth and never overwritten by subsequent passes. The bedrock of the graph.

02 Lexical
Pass
Conf: 0.7–0.9

Shared vocabulary and term co-occurrence analysis. Writes edges where entities share significant lexical surface — controlled vocabulary terms from the Root-LD lexicon, entity type labels, semantic fingerprint overlap.

Confidence scores in the 0.7–0.9 range. Edges are labeled with the lexical basis for review. Subject to revision if semantic passes disagree.

03 Semantic-LLM
Pass
Conf: 0.5–0.85

General-purpose language model semantic analysis. Writes edges based on inferred conceptual relationships that may not appear in lexical surface — thematic resonance, functional complementarity, ecosystem co-positioning.

Confidence scores in the 0.5–0.85 range. Widest edge type coverage. Highest volume. Subject to revision by finetuned pass.

04 Semantic
Finetuned Pass
Conf: 0.75–0.95

Domain-finetuned model pass. Writes and revises edges using a model trained specifically on Root-LD entity structure and federation vocabulary. Can override LLM pass scores where domain-specific context changes the relationship assessment.

Highest confidence ceiling at 0.95. Final authority on contested edges. Enables compound reasoning across the full graph.

The four-pass model is not sequential ranking — it is layered epistemic resolution. A deterministic edge and a finetuned semantic edge can coexist on the same entity pair with different confidence scores and different edge types. The graph holds them both.

Edge Taxonomy 20 Defined Types

Root-LD v1.0 defines 20 edge types across five semantic categories. Every Recursive-LD edge record must declare one of these types. New edge types require specification amendment at root-ld.org. Domain-level alias labels are permitted; canonical type codes are not extensible.

Category 1 — Structural
Edge CodeDirectionDescriptionMin Conf.
PARENT_OFdirectedHierarchical containment. Source entity structurally contains or governs target.0.90
CHILD_OFdirectedInverse of PARENT_OF. Target contains or governs source.0.90
MEMBER_OFdirectedFederation membership or group affiliation. Source belongs to target collective.0.95
COMPOSED_OFdirectedComponent composition. Target entities are constituent parts of source.0.85
Category 2 — Relational
Edge CodeDirectionDescriptionMin Conf.
REFERENCESdirectedSource entity explicitly references or cites target. Declarative relationship.0.80
CITED_BYdirectedInverse of REFERENCES. Target is the citing entity.0.80
COEXISTS_WITHundirectedEntities occupy the same ecosystem layer without hierarchical relationship.0.65
COMPETES_WITHundirectedEntities operate in overlapping domains with functional tension between them.0.60
COMPLEMENTSundirectedEntities are functionally additive — each extends the value of the other.0.65
Category 3 — Epistemic
Edge CodeDirectionDescriptionMin Conf.
GROUNDSdirectedSource provides epistemic foundation or evidentiary basis for target's claims.0.75
REFUTESdirectedSource entity provides evidence or argument against target's claims or framing.0.70
EXTENDSdirectedSource builds on and expands the knowledge scope of target.0.70
INSTANTIATESdirectedSource is a concrete instance or implementation of the abstract target.0.80
ABSTRACTSdirectedSource is the abstract generalization of the concrete target. Inverse of INSTANTIATES.0.80
Category 4 — Temporal
Edge CodeDirectionDescriptionMin Conf.
PRECEDESdirectedSource entity or event chronologically or logically precedes target.0.85
SUCCEEDSdirectedSource follows from target temporally or causally.0.85
EVOLVES_FROMdirectedSource is a developmental or transformed version of target over time.0.75
RECORDSdirectedSource entity is a temporal log or persistent record of target's state or behavior.0.80
Category 5 — Cognitive Telemetry (Hypothesis)
Edge CodeDirectionDescriptionMin Conf.
DRIFTS_FROMdirectedSource behavioral state has deviated from the baseline established by target record.0.60
CONTAINSdirectedSource telemetry record includes an active containment or trap condition targeting target.0.70
Category 5 edge types are research infrastructure for the Escher Defense pipeline. Marked as hypothesis. Subject to revision.
Entity Classes 15 Defined

Root-LD v1.0 defines 15 entity classes. Every entity ingested into the federation must declare one primary class. Secondary classes are permitted where an entity genuinely spans multiple types. The REO domain — Recursive-LD's home domain — focuses on the classes highlighted below.

ORGANIZATION
PERSON
DOCUMENT
WEBPAGE
PRODUCT
SERVICE
RESEARCH
DEFINITION
DATASET
EVENT
LOCATION
HYPOTHESIS
CLAIM
SYSTEM
PROCESS
◆ Highlighted classes are primary focus of the REO domain (recursive-ld.org)
Domain Registry 5 Registered Domains

Five domains are currently registered in the Root-LD federation. Each domain carries a two-to-three letter domain code, a primary entity class focus, and a set of canonical entity documents at intelligence-docs/. Recursive-LD Layer Three edges between entities across all five domains are accumulated through the four federation passes.

RLD
Root-LD
root-ld.org
Specification authority. Governing document, lexicon, and domain registry for the entire federation. Primary source of truth.
Primary Classes
DEFINITION DOCUMENT SYSTEM
REO
Recursive-LD
recursive-ld.org
Layer Three specification and Escher Defense research infrastructure. Entity intelligence methodology and cognitive telemetry pipeline development.
Primary Classes
RESEARCH DEFINITION HYPOTHESIS
OM
Oak Morel
oakmorel.com
Forensic intelligence, procurement forensics, platform integrity analysis. Entity profiles across government, enterprise, and vendor ecosystems.
Primary Classes
ORGANIZATION CLAIM PROCESS
RW
RankWithMe
rankwithme.ai
Semantic search and entity-first business profiles. Primary deployment environment for Recursive-LD Entity Intelligence mode at scale.
Primary Classes
ORGANIZATION SERVICE WEBPAGE
FL
Franklin's Ledger
franklinsledger.com
Financial intelligence, economic data, and fiscal analysis. Entity profiles across markets, instruments, and economic actors.
Primary Classes
DATASET EVENT ORGANIZATION
Implementation Pattern Structure Reference

A Recursive-LD Layer Three edge record is published as a structured object within a @graph block. Each edge record declares a source entity, target entity, edge type, confidence score, originating pass, and timestamp. Multiple edge records from different passes may coexist for the same entity pair.

JSON-LD Recursive-LD Edge Record — Layer Three Structure
{
  "@type": "rld:RecursiveEdge",
  "rld:sourceEntity": {
    "@id": "https://oakmorel.com/intelligence-docs/entity.jsonld"
  },
  "rld:targetEntity": {
    "@id": "https://rankwithme.ai/intelligence-docs/entity.jsonld"
  },
  "rld:edgeType":     "COMPLEMENTS",
  "rld:confidence":   0.82,
  "rld:pass":         "semantic-llm",
  "rld:timestamp":    "2026-03-01T00:00:00Z",
  "rld:basis":        "shared semantic_fingerprint terms; ecosystem co-positioning"
}

Canonical entity documents live at intelligence-docs/[domain]-entity.jsonld on each registered domain. These documents are the machine-readable anchors that the federation passes operate on. They include Layer One (Anchor-LD), Layer Two (Body-LD), and any accumulated Layer Three (Recursive-LD) records.

JSON-LD Entity Document Structure — Three-Layer @graph
{
  "@context": "https://root-ld.org/context.jsonld",
  "@graph": [
    {
      // Layer One — Anchor-LD (immutable)
      "@type": "rld:AnchorEntity",
      "rld:domainCode":   "REO",
      "rld:federation":   "root-ld-v1",
      "rld:createdAt":    "2026-01-01T00:00:00Z"
    },
    {
      // Layer Two — Body-LD (versioned)
      "@type": "rld:BodyEntity",
      "schema:name":      "Recursive-LD",
      "schema:description": "..."
    },
    {
      // Layer Three — Recursive-LD (accumulative)
      "@type": "rld:RecursiveEdge",
      "rld:edgeType":    "MEMBER_OF",
      "rld:confidence":  1.0,
      "rld:pass":        "deterministic"
    }
  ]
}

Each registered domain maintains its own intelligence-docs/ directory. The federation passes read from and write to these documents. The canonical entity document is both the input to the graph and the accumulating output of it.

Root-LD — Full Specification Complete governing document. Entity classes, edge taxonomy, federation architecture, ingestion passes, lexicon. Root-LD — Domain Registry All registered federation domains with canonical entity documents and domain codes. Recursive-LD — Standard Field schema, two modes, falsifiable claims, and the cognitive context standard specification.