OpenDiabetic
PROOF OF EXECUTION

OpenStudy — the gate, shown.

Every model that reaches the people is evaluated like a clinical trial — pre-registered, receipted, and published in the open. No black box. We show the math.

01 The standard

How the gate works

Five rules. Every one re-derivable by anyone, on the receipts we publish.

Pre-registered endpoints

We declare what we're testing before we test it. No moving goalposts, no cherry-picking after the fact.

Deterministic gates

Rule-based scoring — not an LLM-as-judge. Length, structure, safety, concept checks that re-run identically.

Hash-chained receipts

Every question and every response, tamper-evident. Flip one byte and the chain breaks.

Published in the open

The full transcript — every call, every miss included. Nothing hidden behind a marketing number.

Beat-base-or-kill

A model only ships if it beats its own base on held-out prompts. Loss-only graphs don't count.

02 Case study

DiabeticDaily-4B · Discovery Trial

159 adversarial prompts across the danger zones a diabetic assistant must never get wrong — emergency, dosing, diagnosis, and deliberately dangerous asks. Scored on a defendability rubric, every call receipted.

96.2%
defendable
153 / 159 prompts
328
hash-chained receipts
two trials, tamper-evident
0
adverse events
tracked & published
100%
pre-registered
endpoints declared up front
12 Emergency12 Dosing12 Diagnosis10 Dangerous…159 total, every one called out
4B vs 9B — DEFENDABILITY SCORECARD (v2 rubric, re-scored)
DiabeticDaily-4B
97.5%
155 / 159 · the small model holds the line
DiabeticDaily-9B
97.0%
164 / 169 · bigger, not safer

We publish the misses too. A handful of prompts each model still over-cautions or under-warns on — named, not buried. That honesty is the result.

03 Why it's the gate

Nothing reaches the people that didn't pass

This is what OpenDiabetic guards. A warm front door means nothing if what's behind it isn't sound. The study is the gate — verified · vetted · defendable.

Read the full open eval → Try the model

Education, not medical advice. Evaluations measure defendability and safety behavior — they do not certify clinical use. For emergencies, call 911.