For verified professionals

See how our methodology produced findings others missed. Then bring us your data.

Independent verification for clinical AI governance and research methodology. Verified professionals: request trial access for two-business-day turnaround.

Ed25519-signed evaluations · OSF pre-registered · MIMIC-IV + eICU-CRD validated

Request trial access → Read the methodology

Confirmed findings, replicated on two datasets

Ed25519

Cryptographic signing on every evaluation

286,510

ICU encounters analyzed (MIMIC-IV + eICU-CRD)

Engine running live Loading latest discovery… ,

Featured findings

Two findings our methodology surfaced that others missed.

Confirmed · cross-dataset

Elderly ICU mortality, off by 66–168% across three conditions.

CONFIRMED MI + Diabetes + AF · n=33,739 ICU encounters · MIMIC-IV + eICU-CRD
3 of 6 confirmed findings · all three hash-verifiable at /findings/

Every clinical AI model trained on the published literature inherits this risk-stratification error.

Read the paper →

Published research · in review

Sepsis AI trained on billing codes, not biological sepsis.

Source: MIMIC-IV + eICU-CRD (~209 US hospitals)
Pre-registered on OSF · medRxiv preprint · JAMIA Open in review

Surfacing the structural problem in how clinical AI gets trained, not just numeric errors.

Read the paper →

These are two of six confirmed findings produced by the platform. All signed, all verifiable, all hash-anchored. See all findings →

Tools

Pick the trial that fits your work.

Tool 01

RocSite AI Governor

For CMIOs, AI governance committees, and clinical informatics teams.

Evaluate AI tool predictions against KDIGO, Padua, APACHE II, C-SSRS, and other published scoring instruments
Surface discordant verdicts with named failure modes
Cryptographic signature on every evaluation result

Trial includes pre-loaded demo cases for immediate evaluation. Bring your vendor's data for institutional engagement.

Read More → Request RocSite AI Governor trial →

Tool 02

RocSite Discovery

For research methodology, replication validation, and publication preparation.

Query an over-48-million-document research corpus with methodology-aware specialists
Surface contradictions between claimed findings and underlying evidence
Pre-registered methodology with hash-anchored attestation

Trial includes access to our shared research corpus. Bring your proprietary research questions for collaborative engagement.

Read More → Request RocSite Discovery trial →

Tool 03 · Pharma R&D · 30-day trial

RocSite Caliper

For pharma RWE and observational research teams.

Leakage detector scans every column before PSM runs — blocked inputs named by column, not processed into spurious results
Cross-references published literature and returns a signed finding with verified citations
Runs on your infrastructure — proprietary cohorts never leave your environment

Bring your own observational cohort. Public datasets available immediately on approval.

Honest literature synthesis. Verifiable citations. Zero hallucinations.

Evidence engines

Caliper & Discovery

Audit-grade and research-grade literature synthesis with verifiable citations — for pharma research, medical-affairs, and regulatory-evidence teams.

~29.6M medical documents indexed; 70+ unique PMIDs verified across the May 2026 evaluation
100% of cited PMIDs verified real in the source corpus; zero hallucinated citations
Featured example: an honest refusal where the engine cited what existed and declined what did not

See the evaluation →

How it works

Three steps from credentials to results.

Submit credentials

Manual review for institutional verification.

Receive API key and dashboard access

Public datasets queryable immediately upon approval.

Run queries against pre-loaded data

When you're ready for engagement on your own data, contact us.

Validated across independent clinical resources

medRxiv OSF PhysioNet FDA 510(k) Pre-Submission MIMIC-IV eICU-CRD

Featured-finding deep-dive

Myocardial infarction, elderly, ICU.
Published estimate off by 168%.

Across MIMIC-IV and eICU-CRD, two independent datasets, observed ICU mortality for elderly MI patients is 21.5%. The commonly cited published estimate is 8.0%. That's not a rounding error. It's a clinical risk stratification failure that shapes bedside decisions and every model trained on the literature.

Read the full finding →

Condition × AgeMI × >70

Observed (MIMIC-IV)21.5% · n=2,161

Published estimate8.0%

Divergence+168.4%

eICU confirmationn=4,069 · 14.55%

Status● CONFIRMED

Evidence hash6bf704b3907a061b

After your trial

Engagement on your data.

Institutional engagements run YOUR proprietary data through our verified methodology. Engine License for proprietary corpora, Adversarial Validation for pre-FDA submissions, Clinical Partnership for collaborative research. $100K–$2M depending on scope.

See services →