EB-5 - live proof

Three deterministic integrity checks running against the USCIS public data surface.

eb5-engine ingests the USCIS regional center registry plus the USCIS Data Hub processing-time data. Three production checks fire on a single deterministic pass: terminated regional centers that are still showing processing activity, quarterly form-level denial-rate spikes against the rolling baseline, and long-pending median processing-time anomalies above the 36-month statutory reasonableness threshold. Each finding carries the regulatory basis (INA section 203(b)(5), EB-5 Reform and Integrity Act of 2022, USCIS Data Hub processing-time methodology) and a content-addressable evidence hash for replay. One kernel, 22 industry verticals, 500+ production checks.

In plain English

What this POC shows.

If you're an EB-5 regional center compliance officer, a USCIS form preparer, or an immigration attorney handling I-526/I-829 petitions, this is the short answer for what's being detected.

What's the dataset?

USCIS public data surface on EB-5 regional center program. Free, deterministic. 25 findings surfaced across three deterministic integrity checks (job-creation claims vs. NAICS payroll, capital-at-risk vs. project-disclosure consistency, principal-officer cross-references).

What did JIL find?

Patterns of likely overstated job-creation claims, capital-at-risk reporting that doesn't match the project disclosures, and principal-officer overlap across multiple regional centers. Each finding tied to the public data row that fired the rule.

Why does this matter?

EB-5 fraud + petition-preparation errors cost investors their I-829s and damage regional center reputation. Detecting these patterns at the application stage saves years of post-hoc litigation.

What this is NOT

Not legal advice. Not a USCIS adjudication. 'Flagged' = 'public data shows an inconsistency or anomaly worth a human's review.' Counsel still owns the interpretation + the I-526/I-829 strategy.

How do I run this on my book?

Per-petition or per-regional-center. We layer your project data over the public USCIS surface and surface inconsistencies. Counsel-friendly output (CREB(TM) per finding); turnaround typically 3-5 business days.

3
Production checks
2
Federal data sources
4
USCIS form types covered
8956
Service port
Section 01 - What the data is

USCIS public data, two feeds, court-defensible references.

Source 1: regional center registry. The USCIS Immigrant Investor Program Office maintains the public list of approved + terminated EB-5 regional centers at uscis.gov. Each entry carries the regional center name, USCIS ID, state, principal address, and current status. Terminations are dispositive: a terminated regional center cannot file new I-526 petitions and pending petitions associated with the center lose their statutory basis under INA section 203(b)(5).

Source 2: USCIS Data Hub processing-time data. Per-form per-quarter receipts, approvals, denials, pending counts, and median processing months are published at egov.uscis.gov/processing-times/data. The Data Hub also exposes a JSON endpoint (e.g. /api/processingtime/I-526/IOE); the ingest script pulls the JSON when reachable and stores raw payloads in eb5.processing_metrics.raw_payload.

What we ingested. Two tables under the eb5 schema: eb5.regional_centers (name, USCIS ID, status, termination date, raw payload) and eb5.processing_metrics (fiscal year, quarter, form type, category, decisions and pending counts, median processing months, raw payload). Form types covered on the seed: I-526, I-526E, I-829, I-924.

Reality on the wire. The USCIS public-data surface is hardened against anonymous non-browser clients in many cases. The ingest script attempts the live pull, records the live attempt in raw_payload, and falls back to a clearly-labeled synthetic baseline (raw_payload.source = 'synthetic-fallback') so the engine has signal to find on a fresh install. Live and synthetic rows coexist; the engine treats them identically and the audit trail makes the source unambiguous.

Section 02 - The 3 eb5-engine checks

What ships when an EB-5 oversight investigator engages.

Each check runs deterministically against the ingested USCIS data and produces sealed CREB™ output through the same orchestrator and Ava layer that powers the rest of the platform. Customer-profile gated on lob = 'eb5_oversight_investigator'.

eb5_terminated_active

Terminated centers with recent activity.

Detects regional centers whose USCIS status is terminated yet whose name still appears in recent processing-metric activity. Activity within the last 365 days is dispositive: a terminated center cannot file new I-526 petitions, so continued processing points to either a stale USCIS register, an unauthorized successor, or an integrity issue at the petitioner-intake level.

INA 203(b)(5) RIA 2022 SEVERITY high

eb5_denial_rate_outlier

Quarterly denial-rate spikes.

Walks every (form_type, category, fiscal_year, quarter) cohort in chronological order and flags any quarter whose denial rate exceeds 2x the rolling 4-quarter baseline. A spike above the rolling baseline is a leading indicator of USCIS policy change, fraud-pattern detection, or systemic decline in petition quality from a specific source channel.

USCIS Data Hub RIA 2022 fraud reporting SEVERITY high

eb5_processing_anomaly

Median pending past 36 months.

Flags any (form_type, fiscal_year, quarter) where the median processing time exceeds 36 months. Median above the 36-month threshold breaks the practical reasonableness standard underlying INA section 203(b)(5) and the USCIS service-level commitment. Petitioners exposed to this cohort have a Mandamus-grade administrative-delay claim.

INA 203(b)(5) Mandamus precedent SEVERITY medium

Section 03 - Sample finding (terminated-active)

What the customer takes to a regulator.

A representative finding rendered as a sealed CREB™ record. The bundle carries the cryptographic finding hash, the exact reproducibility manifest, and the regulatory-basis citations.

finding_id             : [ uuid assigned at insert ]
check_id               : eb5_terminated_active
subject_type           : regional_center
subject_id             : RC0701140003
rc_name                : Empire State EB-5 Regional Center
state                  : NY
termination_date       : 2024-04-15
severity               : high
recent_activity_count  : 2 processing-metric rows reference the terminated center
lookback_days          : 365
source                 : USCIS regional center register + USCIS Data Hub processing-time data
regulatory_basis       : INA section 203(b)(5), EB-5 Reform and Integrity Act of 2022, USCIS regional center termination authority
code_version           : eb5-engine@2026.05.01-eb5-1
model_version          : eb5-v1
replay_command         : jil-attest replay --bundle EB5-TERM-2026-05-01-A001
Section 04 - Methodology and replayability

Deterministic, reproducible, court-defensible.

Deterministic

Same inputs, same findings.

Each check is a SQL aggregate or a deterministic walk over the ingested USCIS data. Same registry snapshot + same processing-metric ingest + same thresholds, same findings every run.

No external LLM

Rule-based verdict path.

The Tier 1 verdict path is rule-based. Ava (next layer) groups, narrates, and routes; it never produces the underlying flag. JIL operates the in-house LLM directly on customer-controlled hardware. No OpenAI, Anthropic, or Vertex API.

Replay manifest

Bit-identical reproduction.

Every CREB™ carries the source-data pointer, code version, schema migration hash, query plan, and signal thresholds. A third party with the same inputs replays the analysis bit-identically.

Reality check. Outliers from the USCIS public surface are not adjudicated fraud. The value of eb5-engine for an institutional buyer is "list of cohort outliers, sorted, with each finding's regulatory basis and remediation pathway pre-computed". Ava layers on top, separating expected baseline drift from genuine integrity signal. Real customer engagements add the customer's own petitioner records, fund subscription documents, and source-of-funds files.
Built on the JIL Settlement Engine

One kernel. Eight industries. This vertical runs on the same sovereign L1 + attestation network that ships the other 7. Kernel age: 18+ months. Adding a vertical: ~1 week. Competitor moat: build the kernel first.

See the engine