Unconfound Labs
Capability Statement

Unconfound Labs LLC

Epidemiological and causal-inference method applied to administrative, surveillance and registry data. Evidence a program office can act on.

CAGE
22GK8
UEI
Z8AXDFDPAAP2
Business type
Small Business, Woman-owned
NAICS
541511 Custom Computer Programming541512 Computer Systems Design541611 Management Consulting541720 R&D, Social Sciences
Core Competencies

Data analysis, statistics and visualization

Study design, modeling, reporting on large administrative and public-use data. Built for non-technical reviewers.

Record linkage and entity resolution

Linking records with no common identifier. Linkage error quantified, not assumed.

Bias measurement and validation

Real effect separated from measurement, linkage and instrument artifact.

Data architecture and enterprise modeling

Relational schemas, multi-system pipelines, regulated-data foundations.

Unstructured to structured extraction

NLP over case files, clinical literature, technical documentation. Citation locking.

Synthetic data with known ground truth

Realistic cohorts where accuracy is measured, not asserted.

Privacy-first agentic AI

Open-weights models behind the client firewall. Controlled data never leaves the boundary.

Past Performance

Formed May 2026. Five completed methods analyses: BRFSS, NSCH, FAERS, IDEA Part B, and synthetic linkage cohorts, public at github.com/UnconfoundLabs. Master's thesis work partnered with CDC / ATSDR. SBIR Phase I submitted 2026 to the Department of Education (IES) and the Air Force.

Differentiators

Methodological rigor

Replicated methods papers and analyses with responsible AI use. Public at github.com/UnconfoundLabs.

Principal investigator credentials

MHS epidemiology, Johns Hopkins. MPH, Emory. Doctoral training in epidemiology and data science.

Sized for small awards

One accountable technical principal. No subcontractor overhead.

Cleared for controlled technical data

JCP / DD Form 2345 approved August 2026. CMMC Level 2 self-assessment posted to SPRS.

Registrations & Details
Registrations
SAM.gov active
SPRS and DIBBS
JCP / DD Form 2345 approved August 2026
CMMC Level 2 self-assessment posted to SPRS
Payment
Accepts Government Purchase Card
(Visa and Mastercard)
Company data
Maryland LLC, formed May 2026
UEI Z8AXDFDPAAP2 · CAGE 22GK8
Small Business, Woman-owned
Stack
Python, SQL, AWS
Local LLM orchestration
Claude Code / MCP
Contact
Principal
Hannah Choi, Principal
[email protected]
443-712-1338
Address
306 W Redwood St STE 201
Baltimore, MD 21201
github.com/UnconfoundLabs