Reads as: riskier than 49.9% 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
1
Kind
Finding
Signal
Subject
First seen
connection
Owner spans multiple chains
4 chains
POWERBACK REHABILITATION LLC
32 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 lease_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
FL median
National median
National p25–p75
Total nurse
3.17
3.42
3.28
2.90–3.77
RN
0.33
0.45
0.39
0.25–0.58
Weekend total
3.08
3.31
3.11
—
Weekday total
3.20
3.48
3.35
—
Quarter
Days
Avg census
Total HPRD
RN
LPN
CNA
Weekend
Contract %
2025Q4
92
57.6
3.17
0.33
0.76
2.08
3.08
0.0%
2025Q3
92
56.5
3.20
0.41
0.68
2.12
3.15
0.0%
2025Q2
91
59.8
3.02
0.46
0.56
2.00
2.91
0.0%
2025Q1
90
58.6
3.16
0.44
0.64
2.08
3.09
0.0%
2024Q4
92
58.6
3.15
0.39
0.69
2.08
3.07
0.0%
2024Q3
92
56.4
3.22
0.34
0.74
2.14
3.11
0.0%
2024Q2
91
57.1
3.25
0.34
0.76
2.15
3.15
0.0%
2024Q1
91
56.4
3.25
0.48
0.59
2.18
3.13
0.0%
2023Q4
92
55.0
3.25
0.48
0.57
2.20
3.10
0.0%
2023Q3
92
54.2
3.23
0.48
0.58
2.17
3.15
0.2%
2023Q2
91
53.6
3.29
0.35
0.74
2.20
3.17
0.0%
2023Q1
90
57.9
3.29
0.29
0.77
2.23
3.26
0.0%
2022Q4
92
58.3
3.04
0.34
0.71
1.98
3.03
0.1%
2022Q3
92
58.0
2.98
0.31
0.75
1.92
2.95
2.4%
2022Q2
91
56.9
2.96
0.27
0.84
1.85
2.83
3.5%
2022Q1
90
57.7
3.10
0.38
0.72
2.00
3.15
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
11
D × 7F × 4
deficiencies by survey year
Survey
Type
Tag
Deficiency
Scope
Corrected
2026-03-12
Health
F0803
Ensure menus must meet the nutritional needs of residents, be prepared in advance, be followed, be updated, be reviewed by dietician, and meet the needs of the resident.
F
2026-05-07
2026-03-12
Health
F0812
Procure food from sources approved or considered satisfactory and store, prepare, distribute and serve food in accordance with professional standards.
F
2026-05-07
2026-03-12
Health
F0842
Safeguard resident-identifiable information and/or maintain medical records on each resident that are in accordance with accepted professional standards.
D
2026-05-07
2026-03-12
Health
F0880
Provide and implement an infection prevention and control program.
D
2026-05-07
2024-05-02
Health
F0644
Coordinate assessments with the pre-admission screening and resident review program; and referring for services as needed.
D
2024-05-31
2024-05-02
Health · complaint
F0661
Ensure necessary information is communicated to the resident, and receiving health care provider at the time of a planned discharge.
D
2024-05-31
2024-05-02
Health
F0801
Employ sufficient staff with the appropriate competencies and skills sets to carry out the functions of the food and nutrition service, including a qualified dietician.
D
2024-05-31
2024-05-02
Health
F0804
Ensure food and drink is palatable, attractive, and at a safe and appetizing temperature.
F
2024-05-31
2022-05-12
Health
F0757
Ensure each resident’s drug regimen must be free from unnecessary drugs.
D
2022-06-05
2022-05-12
Health
F0760
Ensure that residents are free from significant medication errors.
D
2022-06-05
2022-05-12
Health
F0812
Procure food from sources approved or considered satisfactory and store, prepare, distribute and serve food in accordance with professional standards.
F
2022-06-05
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
28
Owner
Role
Pct
From
Status
Source
THE PAVILION AT JACKSONVILLE PROPERT
Individual has financial interest in both related organization and provider
100%
2023-01-01
current
hcris_a_8_1
THE PAVILION AT JACKSONVILLE PROPERT
Individual has financial interest in both related organization and provider
100%
2024-01-01
current
hcris_a_8_1
BIRNBAUM, EZRA
INDIRECT OWNERSHIP INTEREST
—
2021-05-01
current
pecos_ownership
FASTEN HALBERSTAM LLP
ADP OF THE SNF
—
2021-05-28
current
pecos_ownership
FTK CAPITAL LLC
INDIRECT OWNERSHIP INTEREST
—
2021-05-01
current
pecos_ownership
HIRSCH, SHAYE
INDIRECT OWNERSHIP INTEREST
—
2021-05-01
current
pecos_ownership
INZELBUCH, AZRIEL
INDIRECT OWNERSHIP INTEREST
—
2021-05-01
current
pecos_ownership
KRIESER, AKIVA
OPERATIONAL/MANAGERIAL CONTROL
—
2021-05-01
current
pecos_ownership
LEWIS, JOSEPH
ADP OF THE SNF
—
2024-02-26
current
pecos_ownership
MOERMAN, RAFAEL
OPERATIONAL/MANAGERIAL CONTROL
—
2021-05-01
current
pecos_ownership
NPNH1 LLC
INDIRECT OWNERSHIP INTEREST
—
2021-05-01
current
pecos_ownership
PAVILION HOLDINGS LLC
DIRECT OWNERSHIP INTEREST
—
2021-03-03
current
pecos_ownership
PAVILION MANAGEMENT GROUP LLC
ADP OF THE SNF
—
2021-05-28
current
pecos_ownership
POWERBACK REHABILITATION LLC
ADP OF THE SNF
—
2021-05-28
current
pecos_ownership
RICHARDS MITCHELL & CROSS PA
ADP OF THE SNF
—
2021-05-28
current
pecos_ownership
SHS KEREN LLC
INDIRECT OWNERSHIP INTEREST
—
2021-05-01
current
pecos_ownership
SINGER, SIMON
INDIRECT OWNERSHIP INTEREST
—
2021-05-01
current
pecos_ownership
YU, ZHI
ADP OF THE SNF
—
2021-05-28
current
pecos_ownership
THE PAVILION AT JACKSONVILLE PROPERT
Individual has financial interest in both related organization and provider
100%
2022-01-01
ended 2022-12-31
hcris_a_8_1
THE PAVILION AT JACKSONVILLE PROPERT
Individual has financial interest in both related organization and provider
100%
2021-05-01
ended 2021-12-31
hcris_a_8_1
RAFAEL MOERMAN
INDIRECT OWNERSHIP INTEREST
35%
2021-05-01
ended 2026-05-18
pecos_ownership
EZRA BIRNBAUM
INDIRECT OWNERSHIP INTEREST
23%
2021-05-01
ended 2026-05-18
pecos_ownership
SIMON SINGER
INDIRECT OWNERSHIP INTEREST
23%
2021-05-01
ended 2026-05-18
pecos_ownership
AZRIEL INZELBUCH
INDIRECT OWNERSHIP INTEREST
15%
2021-05-01
ended 2026-05-18
pecos_ownership
SHAYE HIRSCH
INDIRECT OWNERSHIP INTEREST
5%
2021-05-01
ended 2026-05-18
pecos_ownership
AKIVA KRIESER
OPERATIONAL/MANAGERIAL CONTROL
—
2021-05-01
ended 2026-05-18
pecos_ownership
JOSEPH LEWIS
OPERATIONAL/MANAGERIAL CONTROL
—
2024-02-26
ended 2026-05-18
pecos_ownership
ZHI YU
ADP OF THE SNF
—
2021-05-28
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
6
FY end
Total allowable
Rent
Home office
Therapy
Staffing
Counterparties
PropCo
2024-12-31
$536,170
$536,170
—
—
—
2
propco
2023-12-31
$656,177
$656,177
—
—
—
2
propco
2022-12-31
$632,161
$632,161
—
—
—
2
propco
2021-12-31
$317,148
$317,148
—
—
—
2
propco
2021-04-30
$158,880
—
$158,880
—
—
3
—
2020-12-31
$464,647
—
$464,647
—
—
3
—
Cost-report related-party spend by fiscal year. has_propco flags real-estate counterparties.
Transactions
1
Close date
Price
Buyer
Seller
Evidence
2021-05-01
—
THE PAVILION AT JACKSONVILLE FOR NURSING AND REHABILITATION LLC
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
35
Geo
Kind
BR
Amount
As of
Source
county 12031
acs median gross
0
$1,218
2024-12-31
CENSUS_ACS5
county 12031
fmr
0
$1,355
2025-10-01
HUD_USER_FMR
county 12031
acs median gross
1
$1,245
2024-12-31
CENSUS_ACS5
county 12031
fmr
1
$1,382
2025-10-01
HUD_USER_FMR
county 12031
acs median gross
2
$1,508
2024-12-31
CENSUS_ACS5
county 12031
fmr
2
$1,658
2025-10-01
HUD_USER_FMR
county 12031
acs median gross
3
$1,665
2024-12-31
CENSUS_ACS5
county 12031
fmr
3
$2,043
2025-10-01
HUD_USER_FMR
county 12031
acs median gross
4
$1,935
2024-12-31
CENSUS_ACS5
county 12031
fmr
4
$2,561
2025-10-01
HUD_USER_FMR
county 12031
acs median gross
5
$1,899
2024-12-31
CENSUS_ACS5
county 12031
acs median gross
$1,475
2024-12-31
CENSUS_ACS5
county 12031
acs recent mover gross
$1,642
2024-12-31
CENSUS_ACS5
zcta 32218
acs median gross
0
$1,242
2024-12-31
CENSUS_ACS5
zcta 32218
acs median gross
1
$1,268
2024-12-31
CENSUS_ACS5
zcta 32218
acs median gross
2
$1,511
2024-12-31
CENSUS_ACS5
zcta 32218
acs median gross
3
$1,570
2024-12-31
CENSUS_ACS5
zcta 32218
acs median gross
4
$2,168
2024-12-31
CENSUS_ACS5
zcta 32218
acs median gross
$1,503
2024-12-31
CENSUS_ACS5
zcta 32218
acs recent mover gross
$1,884
2024-12-31
CENSUS_ACS5
zip 32218
payment standard 110
0
$1,496
2025-10-01
HUD_USER_SAFMR
zip 32218
payment standard 90
0
$1,224
2025-10-01
HUD_USER_SAFMR
zip 32218
safmr
0
$1,360
2025-10-01
HUD_USER_SAFMR
zip 32218
payment standard 110
1
$1,529
2025-10-01
HUD_USER_SAFMR
zip 32218
payment standard 90
1
$1,251
2025-10-01
HUD_USER_SAFMR
zip 32218
safmr
1
$1,390
2025-10-01
HUD_USER_SAFMR
zip 32218
payment standard 110
2
$1,837
2025-10-01
HUD_USER_SAFMR
zip 32218
payment standard 90
2
$1,503
2025-10-01
HUD_USER_SAFMR
zip 32218
safmr
2
$1,670
2025-10-01
HUD_USER_SAFMR
zip 32218
payment standard 110
3
$2,266
2025-10-01
HUD_USER_SAFMR
zip 32218
payment standard 90
3
$1,854
2025-10-01
HUD_USER_SAFMR
zip 32218
safmr
3
$2,060
2025-10-01
HUD_USER_SAFMR
zip 32218
payment standard 110
4
$2,838
2025-10-01
HUD_USER_SAFMR
zip 32218
payment standard 90
4
$2,322
2025-10-01
HUD_USER_SAFMR
zip 32218
safmr
4
$2,580
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.