Proof of concept · Kaikki / Wiktionary build

BaryGraph is a coordinate system for models.

A graph-and-vector architecture for exploratory retrieval: finding not only what is near a query, but which inspectable relation might connect otherwise distant regions of a semantic space.

The problem: similarity is not direction

When a model searches for what is close to a query, it often finds synonyms, familiar associations, and more examples of the same idea. That is useful for lookup, but limited for exploration.

When asked to go further, a model may combine nearby words into a fluent explanation simply because they frequently occur together. The result can look grounded while containing little more than semantic proximity and verbal completion.

Exploration needs a richer coordinate system: one that can locate not only similar concepts, but also relations, tensions, contradictions, and intermediate structures. BaryGraph makes those relationships retrievable. A result may be a bridge, a contradiction, a higher-order pattern, or only a single useful term. It does not require every result to become a full answer.

Most retrieval returns familiar material. BaryGraph returns a coordinate worth investigating.

Exploratory questions do not always need a longer answer. They often need a better next coordinate: a distinction, bridge, or relationship that changes what the question could mean.

Relations are first-class

Two concepts become the children of a BaryEdge, which receives its own stored vector.

Relations of relations

BaryEdges become children of higher-order MetaBary triads, recursing upward into a relational forest.

Contradictions are coordinates

Synonyms show proximity. Opposing terms create direction. BaryGraph preserves some apparent mismatches as navigational tension worth inspecting.

All of it is retrievable

Nodes, edges, contradictions, and triads live in one index, reachable by ordinary nearest-neighbor search.

The idea in one minute

The name borrows from the barycenter in physics: the shared center generated by two bodies is treated as a real location with properties of its own. BaryGraph applies that intuition to semantic relations. It gives models a space containing not only points of similarity, but relational directions and opposing terms.

BaryGraph schema

At the leaf level, a simplified construction is:

v_edge = normalize( q·v₁ + q·v₂ + (1 − q)·v_context )

At higher levels, construction is algebra on vectors already stored in the graph — no new embedding call is required for each recursive step.

Why this is different

Flat vector retrievalBaryGraph retrieval
Finds text or concepts near a queryFinds concepts, relations, contradictions, and higher-order patterns
Primarily rewards semantic similarityRepresents similarity, distance, tension, and opposition
Often returns synonyms or familiar neighborsCan surface a non-synonymic bridge between distant terms
May continue toward a complete answerCan stop at a term, relation, or short hypothesis
Similarity is mostly attached to documentsMeaning can be attached to the relationship between documents
Strong for direct relevance and lookupDesigned to surface bridges, tensions, and intermediate structure
Often preserves the current framingCan introduce tension that challenges the current framing

What models said after testing it

Four independent language models probed the Kaikki proof of concept with open-ended questions and described what they found. These examples illustrate an interaction pattern, not benchmark performance: the system may return a useful bridge, a weak edge, or only a promising term.

“It behaves more like an associative atlas than a question-answering system. It found a genuine invariant across unrelated domains.”

Tester probing coral reefs · legal precedent · error-correcting codes

“The graph refused to let boredom be an absence. It paired it with overstimulation on the same axis. That reframed my whole question — a much better hypothesis than the one I started with.”

Tester probing boredom · ritual · mathematics

“A weak lexical bridge — turn on — prompted a stronger functional reading: redundancy is often latent until activated.”

On the value of an apparently noisy edge

“A de-cliché device.”

On lateral ideation for writing and design

A de-cliché device

Models are good at producing the first plausible association. BaryGraph introduces friction: a distant term, a contradictory relation, or a bridge that is not immediately explainable. It preserves that tension instead of smoothing it into another familiar continuation. The goal is not to make every answer strange, but to prevent familiarity from being mistaken for insight.

Examples from the proof of concept

Measure between ritual and number

A probe around boredom, ritual and counting returned mensural, metrical, cadenced, foot-tapping, time step. The graph supplied the unexpected hinge: meter. The possible coordinate was undifferentiated time → imposed measure → ritual and number, not a synonym for any one of them.

Redundancy as latent resilience

Ecological overlap, duplicate components, repeated message structure and removable legal surplus converged on one distinction: useful redundancy = multiplicity + failure independence.

Networks across substrates

Mycelial networks and internet architecture surfaced anastomosis beside interconnect terms — precise vocabulary for asking which topological properties are substrate-independent.

Contradiction as tension

An inactigram placed against memory / blank looked malformed as a statement, but sharp as a coordinate: recording inactivity means it is no longer blank. The contradiction opened an inspectable direction without claiming a conclusion.

The current build

The Kaikki English proof of concept, built and queried locally.

6.66M
documents indexed
1.74M
sense nodes
2.50M
leaf BaryEdges
~989k
MetaBary triads (L13–L10)

How to think about results

1. Retrieve a coordinate

Ask an open question and inspect nodes, BaryEdges, MetaBary structures, contradictions, parent chains, and weak bridges. Treat the result as a possible direction, not an answer.

2. Follow or reject the tension

Ask what the relation changes. If it reveals a useful distinction or intermediate pattern, investigate it. If it does not survive inspection, reject it.

3. Stop when the coordinate is enough

A useful result may be one term, one relation, or a short hypothesis. Do not expand it merely to satisfy a target answer length.

4. Do the real work

Use sources, domain knowledge, experiments, formal models, or human judgment to decide whether the coordinate deserves development.

What BaryGraph does not claim

A retrieved bridge is not asserted to be true, causal, or explanatory. A BaryGraph result is a prompt for investigation, not a proof. Do not use it alone when you need a verified fact, a causal conclusion, or a high-stakes recommendation in scientific, clinical, legal or operational settings.