Reads as: riskier than 43.5% 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
3
Kind
Finding
Signal
Subject
First seen
connection
Owner spans multiple chains
10 chains
OFFERLE ANDREW
13 facilities
connection
Owner spans multiple chains
6 chains
CASTETTER ANDREA
31 facilities
connection
Owner spans multiple chains
4 chains
BRANDT JOHN
29 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
IN median
National median
National p25–p75
Total nurse
2.79
2.85
3.28
2.90–3.77
RN
0.28
0.40
0.39
0.25–0.58
Weekend total
2.60
2.71
3.11
—
Weekday total
2.87
2.90
3.35
—
Quarter
Days
Avg census
Total HPRD
RN
LPN
CNA
Weekend
Contract %
2025Q4
92
39.4
2.79
0.28
0.87
1.64
2.60
7.1%
2025Q3
92
36.6
2.98
0.32
0.88
1.77
2.75
4.7%
2025Q2
91
36.6
3.06
0.43
0.97
1.66
2.77
3.1%
2025Q1
90
36.9
3.15
0.36
1.00
1.79
2.91
1.8%
2024Q4
92
40.0
3.03
0.33
0.83
1.87
2.55
1.8%
2024Q3
92
43.4
2.86
0.32
0.79
1.74
2.44
2.7%
2024Q2
91
40.0
2.98
0.38
0.73
1.87
2.47
6.4%
2024Q1
91
37.1
3.32
0.25
0.97
2.11
2.78
5.7%
2023Q4
92
38.5
2.95
0.44
1.02
1.48
2.55
9.1%
2023Q3
92
35.0
3.09
0.41
1.14
1.54
2.89
4.3%
2023Q2
91
37.9
3.30
0.45
1.01
1.84
2.73
4.7%
2023Q1
90
39.2
3.29
0.52
0.94
1.83
2.52
2.0%
2022Q4
92
41.5
3.49
0.57
0.98
1.94
2.62
11.3%
2022Q3
92
41.4
2.90
0.60
0.89
1.42
2.37
5.7%
2022Q2
91
39.5
2.96
0.55
0.98
1.43
2.52
2.5%
2022Q1
90
39.8
2.86
0.32
1.09
1.46
2.39
1.5%
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
10
C × 1D × 7E × 2
deficiencies by survey year
Survey
Type
Tag
Deficiency
Scope
Corrected
2025-08-14
Health
F0628
Provide the required documentation or notification related to the resident's needs, appeal rights, or bed-hold policies.
D
2025-09-05
2025-08-14
Health
F0761
Ensure drugs and biologicals used in the facility are labeled in accordance with currently accepted professional principles; and all drugs and biologicals must be stored in locked compartments, separately locked, compartments for controlled drugs.
D
2025-09-05
2024-09-17
Health
F0759
Ensure medication error rates are not 5 percent or greater.
D
2024-10-01
2024-09-17
Health
F0880
Provide and implement an infection prevention and control program.
E
2024-10-01
2023-09-25
Health
F0577
Allow residents to easily view the nursing home's survey results and communicate with advocate agencies.
C
2023-09-26
2023-09-25
Health
F0578
Honor the resident's right to request, refuse, and/or discontinue treatment, to participate in or refuse to participate in experimental research, and to formulate an advance directive.
D
2023-09-26
2023-09-25
Health
F0609
Timely report suspected abuse, neglect, or theft and report the results of the investigation to proper authorities.
D
2023-09-26
2023-09-25
Health
F0759
Ensure medication error rates are not 5 percent or greater.
E
2023-09-26
2023-08-15
Health · complaint
F0602
Protect each resident from the wrongful use of the resident's belongings or money.
D
2023-08-16
2023-08-15
Health · complaint
F0609
Timely report suspected abuse, neglect, or theft and report the results of the investigation to proper authorities.
D
2023-08-16
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
WITHAM MEMORIAL HOSPITAL
5% OR GREATER DIRECT OWNERSHIP INTEREST
100%
2011-11-01
current
pecos_ownership
BAYSTON, BRETT
CORPORATE DIRECTOR
—
2023-01-01
current
pecos_ownership
BRAND, JOHN
CORPORATE DIRECTOR
—
2015-01-01
current
pecos_ownership
BRAVERMAN, KELLY
CORPORATE OFFICER
—
2021-12-01
current
pecos_ownership
CASTETTER, ANDREA
CORPORATE DIRECTOR
—
2023-01-01
current
pecos_ownership
HAWKINS, CLAUDE
CORPORATE DIRECTOR
—
2013-09-01
current
pecos_ownership
HORNBECKER, MICHAEL
CORPORATE DIRECTOR
—
2024-01-01
current
pecos_ownership
MAGNOLIA HEALTH MANAGEMENT VII
OPERATIONAL/MANAGERIAL CONTROL
—
2011-11-01
current
pecos_ownership
MAGNOLIA HEALTH SYSTEMS 59, LLC
ADP OF THE SNF
—
2025-11-13
current
pecos_ownership
MAGNOLIA HEALTH SYSTEMS INC
ADP OF THE SNF
—
2011-11-01
current
pecos_ownership
OFFERLE, ANDREW
ADP OF THE SNF
—
2025-10-29
current
pecos_ownership
REAGAN, JULIE
CORPORATE DIRECTOR
—
2024-09-25
current
pecos_ownership
REED, MICHAEL
INDIVIDUAL IS AN OWNER, PARTNER OR TRUSTEE OF ANY ADP OF THE SNF
—
2025-11-13
current
pecos_ownership
REED, STUART
OPERATIONAL/MANAGERIAL CONTROL
—
2011-11-01
current
pecos_ownership
SABRA HEALTH CARE LIMITED PARTNERSHIP
ADP OF THE SNF
—
2011-11-01
current
pecos_ownership
SANDERS, JESSICA
ADP OF THE SNF
—
2025-10-29
current
pecos_ownership
SELLERS, DANIEL
CORPORATE OFFICER
—
2024-06-20
current
pecos_ownership
WARD, JONATHAN
ADP OF THE SNF
—
2011-11-01
current
pecos_ownership
KELLY BRAVERMAN
CORPORATE OFFICER
100%
2021-12-01
ended 2026-05-18
pecos_ownership
ANDREA CASTETTER
CORPORATE DIRECTOR
—
2023-01-01
ended 2026-05-18
pecos_ownership
ANDREW OFFERLE
ADP OF THE SNF
—
2025-10-29
ended 2026-05-18
pecos_ownership
BRETT BAYSTON
CORPORATE DIRECTOR
—
2023-01-01
ended 2026-05-18
pecos_ownership
CLAUDE HAWKINS
CORPORATE DIRECTOR
—
2013-09-01
ended 2026-05-18
pecos_ownership
DANIEL SELLERS
CORPORATE OFFICER
—
2024-06-20
ended 2026-05-18
pecos_ownership
JESSICA SANDERS
OPERATIONAL/MANAGERIAL CONTROL
—
2025-10-29
ended 2026-05-18
pecos_ownership
JOHN BRAND
CORPORATE DIRECTOR
—
2015-01-01
ended 2026-05-18
pecos_ownership
JONATHAN WARD
ADP OF THE SNF
—
2011-11-01
ended 2026-05-18
pecos_ownership
JULIE REAGAN
CORPORATE DIRECTOR
—
2024-09-25
ended 2026-05-18
pecos_ownership
MICHAEL HORNBECKER
CORPORATE DIRECTOR
—
2024-01-01
ended 2026-05-18
pecos_ownership
STUART REED
OPERATIONAL/MANAGERIAL CONTROL
—
2011-11-01
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
$685,824
—
$192,091
$493,733
—
15
—
2023-12-31
$841,608
—
$266,381
$453,506
$121,721
15
—
2022-12-31
$810,691
—
$265,906
$425,548
$119,237
15
—
2021-12-31
$674,656
—
$226,757
$397,788
$50,111
15
—
2020-12-31
$708,013
—
—
$439,235
$50,111
15
—
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
30
Geo
Kind
BR
Amount
As of
Source
county 18053
fmr
0
$698
2025-10-01
HUD_USER_FMR
county 18053
acs median gross
1
$622
2024-12-31
CENSUS_ACS5
county 18053
fmr
1
$767
2025-10-01
HUD_USER_FMR
county 18053
acs median gross
2
$838
2024-12-31
CENSUS_ACS5
county 18053
fmr
2
$956
2025-10-01
HUD_USER_FMR
county 18053
acs median gross
3
$1,005
2024-12-31
CENSUS_ACS5
county 18053
fmr
3
$1,257
2025-10-01
HUD_USER_FMR
county 18053
acs median gross
4
$1,113
2024-12-31
CENSUS_ACS5
county 18053
fmr
4
$1,412
2025-10-01
HUD_USER_FMR
county 18053
acs median gross
$853
2024-12-31
CENSUS_ACS5
county 18053
acs recent mover gross
$1,067
2024-12-31
CENSUS_ACS5
zcta 46933
acs median gross
1
$635
2024-12-31
CENSUS_ACS5
zcta 46933
acs median gross
2
$681
2024-12-31
CENSUS_ACS5
zcta 46933
acs median gross
3
$1,162
2024-12-31
CENSUS_ACS5
zcta 46933
acs median gross
$901
2024-12-31
CENSUS_ACS5
zip 46933
payment standard 110
0
$792
2025-10-01
HUD_USER_SAFMR
zip 46933
payment standard 90
0
$648
2025-10-01
HUD_USER_SAFMR
zip 46933
safmr
0
$720
2025-10-01
HUD_USER_SAFMR
zip 46933
payment standard 110
1
$869
2025-10-01
HUD_USER_SAFMR
zip 46933
payment standard 90
1
$711
2025-10-01
HUD_USER_SAFMR
zip 46933
safmr
1
$790
2025-10-01
HUD_USER_SAFMR
zip 46933
payment standard 110
2
$1,089
2025-10-01
HUD_USER_SAFMR
zip 46933
payment standard 90
2
$891
2025-10-01
HUD_USER_SAFMR
zip 46933
safmr
2
$990
2025-10-01
HUD_USER_SAFMR
zip 46933
payment standard 110
3
$1,430
2025-10-01
HUD_USER_SAFMR
zip 46933
payment standard 90
3
$1,170
2025-10-01
HUD_USER_SAFMR
zip 46933
safmr
3
$1,300
2025-10-01
HUD_USER_SAFMR
zip 46933
payment standard 110
4
$1,606
2025-10-01
HUD_USER_SAFMR
zip 46933
payment standard 90
4
$1,314
2025-10-01
HUD_USER_SAFMR
zip 46933
safmr
4
$1,460
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.