Encoder
Built to measure meaning,
not approximate it.

The VERITY encoder measures 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 meaning into a single similarity score. That compression is a design choice, and it has consequences. Contrasts that change the claim (a denial, a swapped actor, a weaker commitment, a broader or narrower statement) get blurred together. 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 measurement perspectives, and that disagreement is not noise to hide. It is information. When perspectives conflict, that conflict is more informative than any single confidence score. The encoder was built to report that conflict, not collapse it.

What it does

Independent measurement.
Honest disagreement.

The encoder measures text across independent perspectives simultaneously. When they agree, confidence is high. When they disagree, the system flags the conflict and says so.

01
Denial changes the claim
The presence of "not" does not simply invert a word. It inverts the meaning of the entire clause. "Authorized" and "unauthorized" are treated as opposite claims, not as near-identical phrases that share a root.
02
Who did what matters
"The lawyer defended the client" and "the client defended the lawyer" contain the same words, but opposite meanings. The encoder keeps those claims distinct. Similarity systems often treat them as near-identical.
03
How sure is measured
There is a real difference between "this will happen," "this should happen," and "this might happen." The encoder preserves that difference instead of collapsing strength of claim into one similarity score.
04
How broad is measured
"All data is encrypted" and "no data is encrypted" have identical structure and almost identical words. They have opposite meanings. The encoder treats breadth of claim as a meaning distinction, not an afterthought.
Semantic Fidelity Benchmark

Can your encoder tell when meaning changes?

The Semantic Fidelity Benchmark tests whether an embedding system can tell when a claim actually changes: opposites, swapped actors, and broader or narrower statements. Those are the discriminations similarity-based systems structurally struggle to 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. Compare a claim with its opposite, swap who acted, change how strong or how broad the claim is, and see the discrimination live.

Request early access →