Sound Prediction Mako Extractor reads documents and pulls out named entities and the relationships between them — at transformer-beating accuracy, on a single CPU.
transformer, on CPUi
transformeri
The Mako Extractor isn’t a smaller neural network — it’s a different kind of model entirely. It’s built on a new statistical technique born from a convergence of ideas in Bayesian inference and statistical physics: a method that is accurate and fast precisely because it is transparent, not in spite of it. You get a model you can read, audit, and run anywhere — not one you have to take on faith.
Most extractors hand you a black box: entities appear, relations appear, and you take it on faith. Mako shows the named evidence behind each decision — auditable by construction.
And this is not explainable-AI bolted onto a black box. Post-hoc methods like SHAP and LIME approximate a neural network from the outside — and can be unfaithful to what the model actually did. Mako has nothing to approximate: the explanation is the computation. Faithful by construction.
A 54-year-old patient with type 2 diabetes was started on metformin 500 mg and lisinopril for hypertension after presenting with chest pain.
-pril suffix marks ACE inhibitors · matches a drug ontology · sits in a prescribing context after “started on.”
A Drug and a Condition joined by the cue “for” — the strongest learned signal for a treatment relation.
Acme Corp acquired Nimbus Labs for $400 million, a deal led by Dana Reyes in San Francisco.
Corp head-token · title-case shape · it is the subject of “acquired,” a corporate-action verb.
Two Organizations bridged by the verb “acquired” in subject–object order — a directed acquisition relation.
Runs in real time on a single CPU core — no GPU fleet, no per-token bill. Extract at the speed of your pipeline, not your budget.
Every entity and relation traces back to named features you can read. For healthcare, legal, and finance, “why” is not optional — and there is no neural net to explain away.
A model small enough to run inside your environment, on-prem or air-gapped. Your documents never have to leave.
Matches or exceeds fine-tuned transformer extractors on entities and relations — and on clinical text, it leads.
| Capability | Mako Extractor | Typical transformer extractor |
|---|---|---|
| Speed (CPU) | ~75× faster | baseline |
| Model size | ~700× smaller | ~300M params |
| Runs on CPU / on-prem | Yes | GPU-bound |
| Every prediction explained | Yes | No (black box) |
| Entity accuracy | Matches or exceeds | baseline |
| Clinical entity accuracy | Leads | baseline |
| Neural networks / attention | None | Required |
Figures are current internal measurements; final published numbers to be confirmed.
Tell us what you need to extract. We’ll set up a demo on your data, or get you on the early-access list.
Prefer email? info@mederrata.com