1 Scope · 2 Overview · 3 Data model · 4 Serialization · 5 Query semantics · 6 Conformance (L0/L1/L2) · 7 Metadata & versioning · 8 Out of scope · 9 References
This specification defines the structure, serialization, and conformance of a Compressed Knowledge Graph (CKG) — a portable, model-agnostic knowledge layer an AI agent reads before it acts. It defines what a conformant CKG is and how to validate and certify one. It does not define how one is produced.
A CKG is a directed acyclic graph (DAG) of typed domain concepts connected by explicit prerequisite (dependency) edges. Relationships are declared, not inferred — no graph database, no embeddings, no runtime similarity search. A CKG is serialized as plain-text (CSV or Markdown) and is exportable to RDF/Turtle and JSON-LD, so it is human-readable, Git-diffable, and reproducible. It is consumed by deterministic traversal — queried, never summarized.
A node is a single typed domain concept. A conformant node carries:
| Field | Req. | Definition |
|---|---|---|
| ConceptID | MUST | Unique identifier within the graph (integer or stable string). |
| ConceptLabel | MUST | Human-readable concept name. Non-empty. |
| Dependencies | MUST | Pipe-delimited list of prerequisite ConceptIDs (may be empty). Encodes the edges. |
| TaxonomyID | MUST | Category/grouping code for the concept. |
| Confidence | SHOULD | Calibrated score in [0,1]. Required for L2. |
| Provenance | SHOULD | Source citation(s) for the concept. Required for L2. |
An edge is a directed prerequisite/dependency relationship: A depends-on B, declared in A's Dependencies field. Extended typed relationships (enables, causes, gates, contradicts) MAY be layered on the base dependency edge. Every dependency MUST resolve to an existing ConceptID.
ConceptIDs MUST be unique.Dependencies reference MUST resolve to a node in the same graph.ConceptID,ConceptLabel,Dependencies,TaxonomyID 1,Function,,FOUND 2,Domain and Range,1,FOUND 3,Limit,2,CALC # Dependencies: pipe-delimited prerequisite ConceptIDs (e.g. "2|5")
An equivalent human-first serialization: one section per concept, with label, taxonomy, dependencies (as [[links]]), confidence, and source. Lossless round-trip with CSV.
A conformant CKG MAY be exported to RDF/Turtle (concepts as subjects, dependencies as a ckg:prerequisite predicate) and JSON-LD for interoperability with semantic-web tooling. These are views; CSV/Markdown remain canonical.
A conformant client exposes at minimum:
| Operation | Returns |
|---|---|
| list_domains() | Available CKG domains. |
| query_ckg(domain, concept, depth) | The sub-graph of prerequisites and dependents up to depth hops. |
| get_prerequisites(domain, concept) | The full prerequisite chain to root. |
| search_concepts(domain, query) | Concepts matching the query. |
| validate_ckg(graph, profile) | A conformance report (§6). |
Query classes a conformant graph supports: T1 entity lookup · T2 direct dependency · T3 multi-hop path · T4 category aggregation · T5 cross-concept relationship.
Three levels. A graph advances only by meeting the level below it.
| Level | Meaning | Checked by |
|---|---|---|
| L0 | Raw — auto-extracted, unreviewed. | — |
| L1 | Structurally valid (§6.1). | machine — validate_ckg |
| L2 | Authority-certified (§6.2). | a named human authority |
A graph is L1 if and only if it satisfies, machine-checkably:
TaxonomyID.ConceptIDs unique; every Dependencies reference resolves.Confidence ∈ [0,1].An L1 graph becomes L2 when a domain authority reviews it against a Conformance Profile and signs. This is the human-in-the-loop, anti-black-box layer.
A profile, authored by the domain authority (ontologist / SME / brand manager), declares the rules the graph must obey:
validate_ckg(graph, profile) confirms the graph passes L1 and meets the profile's machine-checkable rules → a conformance report.parcels-pursuit-ckg@1.2) with an immutable attestation block (§7).Any prune/add/edit after certification produces a new version (e.g. @1.3) that re-enters review. An L2 attestation binds to exactly one content hash; changing the content invalidates the attestation until re-signed.
A CKG carries a metadata block: name, version (semver), conformance_level (L0/L1/L2), profile (name@version, for L2), attestation (reviewer, timestamp, content hash, for L2), license, and updated. Versioning is semver; any content change increments at least PATCH and resets L2 to pending.
This specification does not define how a CKG is discovered, extracted, or compressed from source material. The automated ontological discovery and compression method — including the retrieval architecture (index-route + full-graph load) — is proprietary and the subject of pending patent applications. Conformance is defined entirely on the artifact, independent of how it was produced. Any process that emits a graph meeting §3–§6 is conformant.
CKG Specification 1.0.0-draft · Graphify.md · © 2026 · format open, method proprietary · draft for review, not for public distribution.