Obligations travel with the weights. The graph decides.
Licence obligations travel with the weights, through every fine-tune, merge and re-upload. ModelBrain keeps that real lineage in FalkorDB and lets the graph decide. A language model may phrase an explanation; it never decides.
- Kinds of graph, one instance
- 3
- Hops of ancestry, max
- 6
- Trust tiers per edge
- 5
- Agents
- 5
§1
One FalkorDB instance, three kinds of graph.
A company's confirmation reaches the hub only as a salted hash. Two different hashes raise an edge to tier 3 for everyone; nobody learns who confirmed.
| Graph | Holds |
|---|---|
| hub | Public facts. Models, DERIVED_FROM edges with trust tiers, licences, clauses, file fingerprints and weight DNA vectors. Never stores which company uses which model. |
| tenant_* | One per company. People, products, deployments, append-only rulings and the facts they rest on, events, tasks and playbooks. Kestrel and Harbor are fictional. |
| sbx_* | One per visitor. A GRAPH.COPY of a fictional company. Everything you click writes here, expires after two hours, and never reaches the demo companies. |
§2
What only the graph engine gives us.
Stop FalkorDB and nothing answers: verdicts return 503, never a cached answer.
- (a)
Many graphs in one instance, GRAPH.COPY
A shared hub, one private graph per company, and a sandbox per visitor cloned in one command. A company's rulings never touch the hub.
- (b)
Vector index inside the graph
1,024 sampled weight values per model, searched with db.idx.vector.queryNodes and filtered by graph properties in the same query.
- (c)
Vector search + traversal + clauses in one query
From a model's weights to its nearest parent, up the trusted ancestry, to the licence clauses: one Cypher statement, a few milliseconds.
- (d)
Bounded variable-length traversal
Every ancestry path up to 6 hops, through merges, at a minimum trust tier; every descendant for the reverse fan-out.
- (e)
Algorithms in Cypher
WCC unmasks re-uploads by shared fingerprints; PageRank ranks relabel hubs; betweenness finds chokepoints; label propagation finds families; shortest path proves a derivation or its absence.
- (f)
Properties on edges, read inside paths
Trust tiers, salted confirmer hashes, weight similarity and merge shares live on the edge; strict mode and merge exposure are enforced in the traversal itself.
§3
Trust tiers on every edge.
Default verdicts use tier 1 and above. Strict mode uses tier 2 and above and answers CANNOT DETERMINE when a parent is only inferred.
| Tier | Evidence for the edge |
|---|---|
| 0 | Weak inference: config fingerprint only |
| 1 | Strong inference: identical file hash, tokenizer + config, or weights that match |
| 2 | Declared on the model card |
| 3 | Confirmed by two independent companies (salted hashes) |
| 4 | Confirmed by the model's author |
§4
Agents and handoffs.
Agents hand work to people through Task nodes. Approving a reopened review writes a new ruling that supersedes the old one.
| Agent | Duty |
|---|---|
| Scout | Ingests a model and its ancestors from the Hub, keyed by canonical id. |
| Resolver | Infers hidden parents from file hashes (WCC) and from the weights (vector search). |
| Auditor | Decides a verdict from the graph and writes an append-only ruling. |
| Watcher | Re-reads watched models, diffs them, and reopens rulings down the lineage. |
| Publisher | Turns a company's confirmation into a salted hash on the shared edge. |
§5
Read the queries.
Every query is in docs/queries.cypher. Try it: weight DNA findings, the Xkev replay, compounding.
Automated screening, not legal advice.