The AdimensionAdimensional Intelligence Research use only
Overview Open clinical-AI research

The Adimension bridges
Human Ingenuity &
Machine Intelligence

Foundation The foundation Letter to the Editor · qyaf038

The DEITY
Principles Framework

Five principles proposed in European Heart Journal — Imaging Methods and Practice. A letter argues a position; it does not measure one. Each line below is what that principle is made to cost in the codebase.

DDataa sha256 travelling with every frame EEthicsa published list of what is not claimed IInformaticscoordinates, and a metric that matches them TTechnologya review tier that needs no weights YYouthe correction is a first-class output

The framework, the letter, and what it does not claim

The position

Built for the ground
that shifts

Clinical AI is usually built to one fixed dimension — one dataset, one regulator, one vendor, one release — and then the ground shifts underneath it.

The Adimension builds for the opposite case. Across imaging, literature, security and reasoning, one choice repeats: structured, inspectable, revisable output rather than a confident opaque answer.

A mask can only be accepted or discarded. Ordered coordinates can be dragged, measured against an expert tracing, and exported — the correction becomes the next training example.

Bridges The work Imaging · literature · reasoning · security · autonomy

The active
bridges

Different domains, one discipline. Each states its own scope, publishes its own numbers, and names the check that could have failed it.

Every repository behind these five, with its real metadata, is in Solutions. Four of them carry an open problem someone else could take.

Methods What repeats across the work Four practices, every bridge

One discipline,
four different domains

Imaging, literature, security and reasoning have little in common on the surface. Underneath, the same four practices carry all of them — and each is an executable assertion rather than a promise in a README.

01What loadedcount the tensors that actually bound 02What raninstalled is not the same as working 03Who gradesa gate the author cannot edit 04The correctionthe export format is the training format

The four practices, and the gate in each project

What is open

What is open,
and what is gated

The clinical adapters are gated on Hugging Face: a research prototype should not slide into clinical use.

Everything else is open — the evaluation, the training records, the pipeline, and a review tier that runs with no weights and no GPU.

Read the ATRIA-EchoTrace evaluation

Research status

Every model here is a research prototype. None is a cleared or approved medical device, and every clinical output needs verification by a qualified specialist.

Scope, measured accuracy and known limits are stated in full on each project page.