Encoder
Built to measure meaning —
not approximate it.

The VERITY encoder is a geometric representation of meaning. Not a similarity engine. A measurement engine. The difference is architectural — and it cannot be closed by scale, data, or fine-tuning.

What it is

A different kind of understanding.

"Every other system encodes text into a position. VERITY encodes text into a measurement. Position is the output. Fidelity is the purpose."

Traditional embedding systems compress all dimensions of meaning into a single vector. That compression is a design choice — and it has consequences. Negation, certainty, agency, and scope are averaged together, then lost. The result is a system that cannot distinguish "the drug is effective" from "the drug is not effective" because both sentences contain the same words, and words are what similarity systems measure.

VERITY was built around a different premise: meaning is not one thing. It is the agreement and disagreement of multiple independent measurements — and that disagreement is not noise to be averaged away. It is the signal. When one dimension sees certainty and another sees doubt, that conflict is more informative than any single confidence score. The encoder was built to preserve that conflict, not collapse it.

What it does

Independent measurement.
Honest disagreement.

The encoder measures text across independent dimensions simultaneously. When dimensions agree, confidence is high. When they disagree, the system knows it has found something worth flagging — and says so.

01
Negation as geometry, not vocabulary
The presence of "not" does not simply invert a word — it inverts the meaning of the entire clause. The encoder represents this as a geometric transformation. "Authorized" and "unauthorized" occupy positions that reflect their meaning, not their shared root.
02
Role and agency are not interchangeable
"The lawyer defended the client" and "the client defended the lawyer" contain the same words and the same relationship — but opposite meanings. The encoder places them in distinct geometric regions. Every other production system treats them as near-identical.
03
Certainty has a spectrum, and it is measured
There is a geometric difference between "this will happen," "this should happen," and "this might happen." The encoder orders certainty correctly — not because it was told the words mean different things, but because it learned that meaning lives in the distance between positions.
04
Scope changes everything
"All data is encrypted" and "no data is encrypted" have identical structure and almost identical words. They have opposite meanings. The encoder treats quantifier scope as a first-class semantic dimension — not an afterthought.
Semantic Fidelity Benchmark

Can your encoder tell when meaning changes?

The Semantic Fidelity Benchmark tests whether an embedding system can distinguish opposites, role reversals, and quantifier shifts — the discriminations that similarity-based architectures structurally cannot make. An expanded 500-pair benchmark with full competitive results is in progress.

0.505VERITYSimLex-999 Spearman ρ
0.460OpenAI text-embedding-3-largeBest competitor

On the standard human-aligned similarity benchmark — which neither system was built to optimize for.

Live Demo

Test the encoder yourself.

An interactive tool for measuring fidelity between any two sentences is coming soon. Enter a statement and its negation, reverse the roles, change the quantifier — and see the discrimination live.

Request early access →