Reads as: riskier than 9.6% of the 14,684 facilities in the snf peer group. percentile within peer group, 100 = highest risk. Grade bands are fixed percentile cuts (F is the top 5% of peer risk), so a grade is a position, not an absolute level.
weighted_contribution sums to pre_rank_index over rows where counts_toward_index is true. The composite is the facility's percentile position of that index within its peer group, so contributions explain the input, and the rank explains the score.
ML signals — parallel engine
11
Kind
Finding
Signal
Subject
First seen
connection
Owner fleet risk far above national
+30.4 vs natl
HAVEN REAL ESTATE PARTNERS LLC
7 facilities
connection
Owner fleet risk far above national
+29.6 vs natl
HAVEN ARIZONA REAL ESTATE LLC
7 facilities
connection
Owner fleet risk far above national
+25.9 vs natl
SAMUELIAN STEPHEN
20 facilities
connection
Owner fleet risk far above national
+22.8 vs natl
WEST CHRISTIAN
31 facilities
connection
Owner fleet risk far above national
+22.4 vs natl
ROBERTSON BRETT
31 facilities
connection
Owner fleet risk far above national
+22.2 vs natl
SAMUELIAN ROBERT
21 facilities
connection
Owner fleet risk far above national
+21.5 vs natl
FRAGOSO LINDSAY
31 facilities
connection
Owner fleet risk far above national
+21.4 vs natl
ESPINOSA STEPHANIE
29 facilities
connection
Owner fleet risk far above national
+21.2 vs natl
SAMUELIAN SPENCER
31 facilities
connection
Owner fleet enforcement cluster
57% fined
HAVEN ARIZONA REAL ESTATE LLC
7 facilities
connection
Owner fleet enforcement cluster
57% fined
HAVEN REAL ESTATE PARTNERS LLC
7 facilities
Findings from the always-on scanning layer: anomalies on this facility, connections through its current owners and past buyers. Runs beside the deterministic composite, never inside it. Full board on the ML Lab page.
Change-of-ownership footprint in the CMS Provider of Services file: control-family, legal-name and address deltas across quarterly snapshots, plus certification reset recency and Medicare tenure.
R23/W4-3. Deterministic logistic p(Medicare termination within 12m), SNF only. Label = first POS termination date (any code: voluntary closure, involuntary termination, merger exit); facilities already terminated by the panel date are excluded, not counted as safe. Trained on panels 2024-07/2024-10/2025-01 (n=46,466, 283 positives), evaluated on the held-out later panel 2025-04 BEFORE shipping: AUC 0.971, top-decile lift 9.5x, top-decile capture 95.4% of the 65 terminations that followed. Separability is high because closures announce themselves in the data: collapsing occupancy is the strongest signal, and the learned NEGATIVE weight on 12m deficiency counts is the surveys-stop signature of a facility winding down, not a claim that clean inspections are dangerous. Same 15 as-of-date features and anti-leakage chassis as p_chow_12m; SFF entry rejected as a label (only one month of SFF history exists, so as-of transitions cannot be reconstructed). Score = probability x 100; grade NULL. Not in any composite.
R22/W4-2. Deterministic logistic p(CHOW within 12m), SNF only. Trained on panels 2024-07/2024-10/2025-01 (n=50,700, 1,207 positives), evaluated on the held-out later panel 2025-04 BEFORE shipping: AUC 0.874, top-decile lift 5.0x (top 10% of predictions captured 49.6% of the CHOWs that actually closed in the next 12 months). Shipped coefficients are the evaluated ones; no post-holdout refit. Caveat: holdout positives (133) run below the training base rate because recent CHOWs surface in public records with a lag, so measured lift is conservative. Features are as-of-date public records: PBJ staffing level/trend/contract share (quarterly history to 2022Q1), deficiency and CMP counts (12m), ownership tenure and churn from CHOW-evidenced transactions, beds, occupancy, ownership type, chain size. Chain membership and ownership type are current-state (history not published). SFF and star ratings deliberately excluded (no as-of history). Notable learned direction: long ownership tenure RAISES sale odds and a recent prior CHOW lowers them. Score = probability x 100; grade is NULL because a probability is not a quality letter. Not in any composite.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later regulatory_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later regulatory_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later staffing_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later staffing_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Rows with counts_toward_composite false come from models that are addressable or retracted rather than default. They exist and may be informative, but they did not enter the published composite and must not be summed as though they had.
p_adverse_action_12m: probability the facility's Medicare participation terminates within 12 months (any POS termination code; already-terminated facilities are excluded, not scored safe). Deterministic logistic over as-of-date public records, SNF only. Holdout (2025-04 panel, evaluated before shipping): AUC 0.971, top-decile lift 9.5x. Closures announce themselves: collapsing occupancy dominates, and fewer recent surveys is a winding-down signature. inputs.features holds raw feature values, inputs.contributions each feature's standardized pull on the log-odds. Predictions never enter the composite. See /v1/models. | p_chow_12m: probability of a change of ownership within 12 months. Deterministic logistic over as-of-date public records, SNF only. Holdout (2025-04 panel, evaluated before shipping): AUC 0.874, top-decile lift 5.0x. inputs.features holds raw feature values, inputs.contributions each feature's standardized pull on the log-odds. Predictions never enter the composite. See /v1/models for full notes.
Probability the facility's Medicare participation ends within 12 months, from public records only. Red bars raise exit odds. A negative pull from deficiencies is the winding-down signature — surveys stop as a facility empties — not evidence that clean inspections are dangerous.
Staffing vs peers
16
2025Q4 HPRD
This facility
AZ median
National median
National p25–p75
Total nurse
2.92
3.53
3.28
2.90–3.77
RN
0.43
0.43
0.39
0.25–0.58
Weekend total
2.80
3.35
3.11
—
Weekday total
2.96
3.62
3.35
—
Quarter
Days
Avg census
Total HPRD
RN
LPN
CNA
Weekend
Contract %
2025Q4
92
53.6
2.92
0.43
0.47
2.02
2.80
0.0%
2025Q3
92
49.7
3.24
0.53
0.51
2.20
3.05
0.0%
2025Q2
91
49.3
3.24
0.47
0.52
2.26
3.10
0.0%
2025Q1
90
51.6
3.26
0.38
0.60
2.27
3.17
0.0%
2024Q4
92
50.3
3.04
0.39
0.62
2.03
2.98
0.0%
2024Q3
92
52.6
2.80
0.41
0.58
1.80
2.67
0.0%
2024Q2
91
54.2
2.83
0.43
0.59
1.82
2.56
0.0%
2024Q1
91
54.5
2.73
0.47
0.52
1.74
2.51
0.0%
2023Q4
92
52.1
2.79
0.54
0.50
1.74
2.52
0.0%
2023Q3
92
51.1
2.85
0.46
0.58
1.80
2.63
0.0%
2023Q2
91
53.5
2.87
0.34
0.61
1.92
2.55
0.0%
2023Q1
90
50.8
3.07
0.46
0.50
2.11
2.62
0.0%
2022Q4
92
55.2
2.71
0.44
0.44
1.82
2.23
0.0%
2022Q3
92
54.3
2.88
0.50
0.41
1.98
2.11
0.0%
2022Q2
91
52.9
3.32
0.46
0.45
2.40
2.86
0.0%
2022Q1
90
55.1
3.16
0.54
0.37
2.25
2.74
0.0%
HPRD is census-weighted: total hours over the quarter divided by total resident-days, not an average of daily ratios. Source is CMS Payroll-Based Journal daily records; only SNFs report PBJ, so other settings legitimately return zero rows.
Penalties
0
No penalties on record for this facility. Absence of a record here means the sources CII ingests contain none, not that none exists anywhere.
Deficiencies
15
D × 13E × 2
deficiencies by survey year
Survey
Type
Tag
Deficiency
Scope
Corrected
2025-11-20
Health · complaint
F0689
Ensure that a nursing home area is free from accident hazards and provides adequate supervision to prevent accidents.
D
2025-12-20
2025-08-28
Health · complaint
F0600
Protect each resident from all types of abuse such as physical, mental, sexual abuse, physical punishment, and neglect by anybody.
D
2025-09-25
2025-08-07
Health
F0583
Keep residents' personal and medical records private and confidential.
D
2025-10-01
2025-08-07
Health
F0609
Timely report suspected abuse, neglect, or theft and report the results of the investigation to proper authorities.
D
2025-09-30
2025-08-07
Health
F0658
Ensure services provided by the nursing facility meet professional standards of quality.
D
2025-10-01
2025-08-07
Health
F0679
Provide activities to meet all resident's needs.
D
2025-10-01
2025-08-07
Health
F0684
Provide appropriate treatment and care according to orders, resident’s preferences and goals.
D
2025-10-01
2025-08-07
Health
F0812
Procure food from sources approved or considered satisfactory and store, prepare, distribute and serve food in accordance with professional standards.
E
2025-10-01
2025-08-07
Health
F0825
Provide or get specialized rehabilitative services as required for a resident.
D
2025-10-01
2025-08-07
Health
F0925
Make sure there is a pest control program to prevent/deal with mice, insects, or other pests.
E
2025-10-01
2024-07-25
Health
F0552
Ensure that residents are fully informed and understand their health status, care and treatments.
D
2024-08-30
2024-07-25
Health
F0695
Provide safe and appropriate respiratory care for a resident when needed.
D
2024-08-30
2023-01-26
Health
F0560
Protect a residents' right to refuse some types of non-requested transfers within the nursing home.
D
2023-03-20
2023-01-26
Health
F0609
Timely report suspected abuse, neglect, or theft and report the results of the investigation to proper authorities.
D
2023-03-20
2023-01-26
Health
F0732
Post nurse staffing information every day.
D
2023-03-20
scope_severity uses the CMS letter grid: A is least serious, L most. J, K and L are immediate jeopardy. Rows are the surveyor's findings of record, not the model's opinion.
Licensure actions
0
No licensure actions on record for this facility. Absence of a record here means the sources CII ingests contain none, not that none exists anywhere.
Ownership
30
Owner
Role
Pct
From
Status
Source
BRAKE, ADAM
OPERATIONAL/MANAGERIAL CONTROL
—
2023-10-03
current
pecos_ownership
ESPINOSA, STEPHANIE
ADP OF THE SNF
—
2024-10-14
current
pecos_ownership
FRAGOSO, LINDSAY
OPERATIONAL/MANAGERIAL CONTROL
—
2021-05-10
current
pecos_ownership
HAVEN ARIZONA REAL ESTATE, LLC
ADP OF THE SNF
—
2013-02-01
current
pecos_ownership
HAVEN DOUGLAS REAL ESTATE LLC
ADP OF THE SNF
—
2013-02-01
current
pecos_ownership
HAVEN REAL ESTATE PARTNERS, LLC
ADP OF THE SNF
—
2013-02-01
current
pecos_ownership
HEALTH GROUP MANAGEMENT LLC
OPERATIONAL/MANAGERIAL CONTROL
—
2013-02-01
current
pecos_ownership
HEALTH GROUP MANAGEMENT LLC
ADP OF THE SNF
—
2025-08-22
current
pecos_ownership
MUIR, MARK
OPERATIONAL/MANAGERIAL CONTROL
—
2015-02-15
current
pecos_ownership
NELSON, NINA
OPERATIONAL/MANAGERIAL CONTROL
—
2013-02-01
current
pecos_ownership
PATEL, PARAG
OPERATIONAL/MANAGERIAL CONTROL
—
2023-01-01
current
pecos_ownership
ROBERTSON, BRETT
ADP OF THE SNF
—
2013-02-01
current
pecos_ownership
SAMUELIAN, ROBERT
OPERATIONAL/MANAGERIAL CONTROL
—
2013-02-01
current
pecos_ownership
SAMUELIAN, SPENCER
ADP OF THE SNF
—
2013-02-01
current
pecos_ownership
SAMUELIAN, STEPHEN
ADP OF THE SNF
—
2013-02-01
current
pecos_ownership
SEASTRAND, JASON
OPERATIONAL/MANAGERIAL CONTROL
—
2013-02-01
current
pecos_ownership
WEST, CHRISTIAN
OPERATIONAL/MANAGERIAL CONTROL
—
2013-02-01
current
pecos_ownership
HAVEN HEALTH GROUP LLC
5% OR GREATER DIRECT OWNERSHIP INTEREST
100%
2013-02-01
ended 2026-05-18
pecos_ownership
STEPHEN SAMUELIAN
5% OR GREATER INDIRECT OWNERSHIP INTEREST
37%
2013-02-01
ended 2026-05-18
pecos_ownership
SPENCER SAMUELIAN
5% OR GREATER INDIRECT OWNERSHIP INTEREST
25%
2013-02-01
ended 2026-05-18
pecos_ownership
ROBERT SAMUELIAN
5% OR GREATER INDIRECT OWNERSHIP INTEREST
20%
2013-02-01
ended 2026-05-18
pecos_ownership
BRETT ROBERTSON
5% OR GREATER INDIRECT OWNERSHIP INTEREST
8%
2013-02-01
ended 2026-05-18
pecos_ownership
CHRISTIAN WEST
5% OR GREATER INDIRECT OWNERSHIP INTEREST
6%
2013-02-01
ended 2026-05-18
pecos_ownership
JASON SEASTRAND
INDIRECT OWNERSHIP INTEREST
4%
2013-02-01
ended 2026-05-18
pecos_ownership
ADAM BRAKE
OPERATIONAL/MANAGERIAL CONTROL
—
2023-10-03
ended 2026-05-18
pecos_ownership
LINDSAY FRAGOSO
OPERATIONAL/MANAGERIAL CONTROL
—
2021-05-10
ended 2026-05-18
pecos_ownership
MARK MUIR
ADP OF THE SNF
—
2015-02-15
ended 2026-05-18
pecos_ownership
NINA NELSON
ADP OF THE SNF
—
2013-02-01
ended 2026-05-18
pecos_ownership
PARAG PATEL
OPERATIONAL/MANAGERIAL CONTROL
—
2023-01-01
ended 2026-05-18
pecos_ownership
STEPHANIE ESPINOSA
OPERATIONAL/MANAGERIAL CONTROL
—
2024-10-14
ended 2026-05-18
pecos_ownership
PECOS ownership and managing-control associations. Current edges have no end date in the source; historical edges are retained.
Related-party costs
5
FY end
Total allowable
Rent
Home office
Therapy
Staffing
Counterparties
PropCo
2024-12-31
$370,005
—
$370,005
—
—
3
—
2023-12-31
$381,617
—
$381,617
—
—
3
—
2022-12-31
$311,581
—
$311,581
—
—
0
—
2021-12-31
$329,693
—
$329,693
—
—
0
—
2020-12-31
$290,720
—
—
—
—
0
—
Cost-report related-party spend by fiscal year. has_propco flags real-estate counterparties.
Transactions
0
No transactions on record for this facility. Absence of a record here means the sources CII ingests contain none, not that none exists anywhere.
Most recent same-state, same-setting trades. Most CHOW-derived trades carry no disclosed consideration, so price, $/bed, and cap rate show only where a sale price was resolved from a deed or filing — blanks are honest, not missing data.
Market rent context
34
Geo
Kind
BR
Amount
As of
Source
county 04003
acs median gross
0
$718
2024-12-31
CENSUS_ACS5
county 04003
fmr
0
$887
2025-10-01
HUD_USER_FMR
county 04003
acs median gross
1
$761
2024-12-31
CENSUS_ACS5
county 04003
fmr
1
$1,111
2025-10-01
HUD_USER_FMR
county 04003
acs median gross
2
$927
2024-12-31
CENSUS_ACS5
county 04003
fmr
2
$1,257
2025-10-01
HUD_USER_FMR
county 04003
acs median gross
3
$1,176
2024-12-31
CENSUS_ACS5
county 04003
fmr
3
$1,748
2025-10-01
HUD_USER_FMR
county 04003
acs median gross
4
$1,650
2024-12-31
CENSUS_ACS5
county 04003
fmr
4
$2,109
2025-10-01
HUD_USER_FMR
county 04003
acs median gross
$995
2024-12-31
CENSUS_ACS5
county 04003
acs recent mover gross
$1,223
2024-12-31
CENSUS_ACS5
zcta 85607
acs median gross
0
$520
2024-12-31
CENSUS_ACS5
zcta 85607
acs median gross
1
$576
2024-12-31
CENSUS_ACS5
zcta 85607
acs median gross
2
$754
2024-12-31
CENSUS_ACS5
zcta 85607
acs median gross
3
$874
2024-12-31
CENSUS_ACS5
zcta 85607
acs median gross
4
$1,382
2024-12-31
CENSUS_ACS5
zcta 85607
acs median gross
$763
2024-12-31
CENSUS_ACS5
zcta 85607
acs recent mover gross
$1,031
2024-12-31
CENSUS_ACS5
zip 85607
payment standard 110
0
$847
2025-10-01
HUD_USER_SAFMR
zip 85607
payment standard 90
0
$693
2025-10-01
HUD_USER_SAFMR
zip 85607
safmr
0
$770
2025-10-01
HUD_USER_SAFMR
zip 85607
payment standard 110
1
$1,078
2025-10-01
HUD_USER_SAFMR
zip 85607
payment standard 90
1
$882
2025-10-01
HUD_USER_SAFMR
zip 85607
safmr
1
$980
2025-10-01
HUD_USER_SAFMR
zip 85607
payment standard 110
2
$1,199
2025-10-01
HUD_USER_SAFMR
zip 85607
payment standard 90
2
$981
2025-10-01
HUD_USER_SAFMR
zip 85607
safmr
2
$1,090
2025-10-01
HUD_USER_SAFMR
zip 85607
payment standard 110
3
$1,672
2025-10-01
HUD_USER_SAFMR
zip 85607
payment standard 90
3
$1,368
2025-10-01
HUD_USER_SAFMR
zip 85607
safmr
3
$1,520
2025-10-01
HUD_USER_SAFMR
zip 85607
payment standard 110
4
$2,002
2025-10-01
HUD_USER_SAFMR
zip 85607
payment standard 90
4
$1,638
2025-10-01
HUD_USER_SAFMR
zip 85607
safmr
4
$1,820
2025-10-01
HUD_USER_SAFMR
ACS median gross rents and HUD FMR/SAFMR for the facility's county and ZIP. Context for underwriting, not facility pricing.