Synthetic warehouse · not for clinical use
Watchdog JSON
Gates every release must pass

Compliance & privacy

Evidence from the latest release v1.0. These checks are synthetic-data controls, not a legal opinion.

Gates
29/29
Realism
100
Quality
100
Watermark
SYNTHETIC-APIARY

integrity

ATL-01 · All five database foreign keys
pass
ATL-02 · Clinical orders equal RX orders
pass
ATL-03 · All paid fills mapped to distribution dispenses
pass
ATL-04 · No negative pharmacy inventory
pass
ATL-05 · Paid claim / dispensation count
pass
ATL-06 · Rx patient plans consistent
pass
ATL-07 · Encounter and prescription patient consistent
pass
ATL-08 · Nonnegative financial splits
pass
ATL-09 · Adherence range valid
pass
ATL-10 · No real provider identifiers
pass
ATL-11 · 100% formulary snapshots matched
pass
ATL-12 · No paid fills for uncovered drug-plan-month
pass
ATL-13 · All medication orders have coverage decision
pass
ATL-14 · No duplicated RX IDs
pass
ATL-15 · No negative monthly stock
pass
ATL-16 · All 5 shared master row counts
pass
ATL-17 · No paid fill without paid claim
pass
ATL-18 · Synthetic flags set
pass
WB-01 · Workbook columns present on every generated source row
pass

licence

WB-03 · MedDRA codes withheld
VOC-05 uses the workbook placeholder, not a numeric MedDRA code.

realism

FID-js_channel · Fidelity plan js_channel
JS divergence on channel versus learned rx.plan. Score 0.003 vs threshold 0.12.
FID-js_coverage · Fidelity formulary js_coverage
JS divergence on coverage_status versus learned rx.formulary_at_order. Score 0 vs threshold 0.08.
FID-js_specialty · Fidelity hcp js_specialty
JS divergence on specialty versus learned rx.hcp. Score 0.002 vs threshold 0.12.
FID-js_state · Fidelity hcp js_state
JS divergence on state versus learned rx.hcp. Score 0.002 vs threshold 0.12.
FID-js_ta_code · Fidelity drug js_ta_code
JS divergence on ta_code versus learned rx.drug. Score 0.032 vs threshold 0.22.
FID-ks_birth_year · Fidelity patient ks_birth_year
Histogram distance on birth year. NSCLC and psoriasis cohorts intentionally shift age, so the threshold is wider than a pure replay. Score 0.044 vs threshold 0.35.
FID-sequence_violation · Fidelity journey sequence_violation
Share of generated journey steps that are absent from the learned transition matrix. Score 0 vs threshold 0.05.
REAL-01 · Realism against the TA calibration bands
female_pct=52.1; age_median=50; biologic_pct=66.3; us_pct=62.5; lot1_pct=64.4; msl_anchored_pct=100

regulatory

WB-02 · Workbook synthetic flag
pass

Vocabulary licence tracker

VOCVocabularyStatusMappingsLicence
EXT-59NCBI Geneopen1NCBI Gene public
VOC-01MeSHopen2NLM MeSH
VOC-02UMLSwithheld1UTS. No redistribution.
VOC-03SNOMED CTwithheld1Affiliate licence. Id not shipped.
VOC-04ICD-10-CMopen1ICD-10-CM public domain. No specific METex14 code; this is the coarse neoplasm code used in the diagnoses table.
VOC-05MedDRAwithheld1MSSO subscription. PT name only.
VOC-06ATC / WHO Drugwithheld1ATC code withheld.
VOC-07RxNormnot_applicable1RxNorm. No code invented.
VOC-09MONDOopen2CC BY
VOC-10SPOR / IDMPwithheld1EMA terms. Not generated.