Skip to content
FonteumPublic-records evidence

Composite quality score

0.00%

Dated output from Fonteum's published quality model.

Across 9 selected source families, model evidence status is incomplete. Missing measurements are omitted, never replaced by a historical constant. Page revalidation runs hourly, but that does not mean an upstream source or model input refreshed hourly. The machine-readable twin lives at /quality.json.

Add Fonteum to your agent →

Per-source quality-model sub-scores

NPPES (NPI registry)

n/a

Completeness n/a · Consistency n/a

Match rate n/a · Timeliness n/a

OIG LEIE exclusions

0.0%

Completeness n/a · Consistency n/a

Match rate n/a · Timeliness 0.0

CMS PECOS PPEF

n/a

Completeness n/a · Consistency n/a

Match rate n/a · Timeliness n/a

CMS Open Payments

n/a

Completeness n/a · Consistency n/a

Match rate n/a · Timeliness n/a

SAM.gov entities

n/a

Completeness n/a · Consistency n/a

Match rate n/a · Timeliness n/a

HRSA HPSA shortage areas

n/a

Completeness n/a · Consistency n/a

Match rate n/a · Timeliness n/a

CMS Care Compare

n/a

Completeness n/a · Consistency n/a

Match rate n/a · Timeliness n/a

BLS OEWS wages

n/a

Completeness n/a · Consistency n/a

Match rate n/a · Timeliness n/a

BEA Regional

n/a

Completeness n/a · Consistency n/a

Match rate n/a · Timeliness n/a

Methodology

How we score

The composite is a weighted mean of four sub-metrics — completeness, consistency, match rate, and timeliness. Inputs can be stored metric rows backed by proved content transitions; unavailable inputs are omitted.

Read methodology v1.3Download PDF (229KB) ↓

Section 1

Per-source completeness

For each source, the median proportion of public-displayable required fields that are non-null and non-empty in the documented measurement. The date below is a stored content-change observation. Families without both a proved transition and a stored completeness measurement are omitted. See the methodology for sampling details.

No transition-backed completeness measurement is available.

Section 2

Inter-source consistency

Where two independent federal feeds describe the same NPI, do they agree? Each rate is the share of NPIs whose normalized value matches across both sources. The denominator is the set of NPIs present in both snapshots with a non-null value on each side.

No cross-source consistency rate is published at this snapshot. The originally-specified NPPES ↔ PECOS checks join enrollment-specialty and enrollment-status fields that are not present in the provider schema, so no reproducible figure exists — and we do not publish a number we cannot recompute. The composite below is renormalized over the families that are published. See the methodology for the full correction note.

Section 3

Temporal update lag

The model reports lag values from source-release and ingestion timestamps when at least two valid content transitions are available in the trailing 90 days. Families without enough transition-backed samples are omitted. These values are model inputs, not a current SLA or proof that every source has a recent ingest.

Source familyMedian lagp95 lagWindow
OIG LEIE exclusions306 h582 h90 d
Section 4

OIG LEIE byte-level match rate

No source/upstream SHA-256 comparison rows are available, so no match rate is published.

Unavailable

evidence status: unavailable

Section 5

Methodology

The composite is a weighted average — 35% completeness, 30% consistency, 20% timeliness, 15% OIG LEIE byte match — pinned at methodology version quality/v1. A family with no reproducible value (currently consistency) is dropped and the remaining weights are renormalized, so the headline never absorbs a missing family as a zero. The methodology identifies formulas, denominators, and evidence-availability rules; readers should not treat the page-revalidation time as a source date.

Read the full methodology →

Machine-readable twins: /quality.json (schema.org Dataset) · /api/v1/quality · Methodology pointer: https://fonteum.com/quality/methodology

READY TO SHIP

Add federal-data citations to your agent in 60 seconds.

Connect the hosted MCP server to your agent, or call the API with an issued bearer credential. See the developer docs for the current public contract.

What’s on file, by the numbers

Platform snapshot · 2026-08-29

13.4Mproviders & companiesProviders, organizations, owners, and facilities on file
26.2Msource-linked factsSource-linked field facts in the dated platform snapshot
90sources with dataDistinct snapshot source IDs with at least one positive record count
19fresh sourcesDistinct source IDs whose latest positive-data snapshot falls within the preceding 45 days
111sources integratedActive registry rows; integration does not establish a load
13state Medicaid jurisdictionsDistinct states represented in the state-exclusions serving table

Integrated, with-data, and fresh-observation counts are separate. No platform-wide source-completeness count is published. Completeness is source-specific and must be evaluated against the named source's expected scope. State coverage is a separate jurisdiction measure.

Source authority is record-specific

Use the issuer named on the record.

Fonteum spans federal, state, and global public publishers. A source page or returned record identifies its issuer and dataset where that metadata is available. A platform registry count does not assign every page to one authority or establish loaded, fresh, or complete coverage.

Browse source records and their stated limitations →

Reproducible by design

Inspect the evidence each published figure actually supplies.

Source and date

Research pages expose the named public file and observation date where those fields are available. Source-file SHA-256 coverage is separate; facts do not currently link deterministically to signatures.

Available derivation

Studies with a retained release and committed derivation link the SQL or method used. Other studies state the evidence and reproduction limits they actually have.

Daily observations

Dated table row-count observations can detect local drift. They do not imply that an upstream publisher released or Fonteum ingested new data that day.

Named medical review

Reviewed by Jennifer Montecillo, MD, medical reviewer. Non-practicing medical reviewer.

Read the full provenance and attestation methodology →

Request access