Reads as: riskier than 23.0% 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 fleet enforcement cluster
56% fined
BYNC HOLDINGS LLC
9 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
NC median
National median
National p25–p75
Total nurse
2.64
3.08
3.28
2.90–3.77
RN
0.24
0.30
0.39
0.25–0.58
Weekend total
2.51
2.93
3.11
—
Weekday total
2.69
3.14
3.35
—
Quarter
Days
Avg census
Total HPRD
RN
LPN
CNA
Weekend
Contract %
2025Q4
92
82.3
2.64
0.24
0.66
1.74
2.51
0.0%
2025Q3
92
81.7
2.88
0.19
0.81
1.88
2.72
0.0%
2025Q2
91
82.9
2.83
0.25
0.70
1.88
2.71
0.0%
2025Q1
90
83.0
2.77
0.23
0.71
1.83
2.64
0.1%
2024Q4
92
80.1
2.77
0.19
0.71
1.87
2.74
0.1%
2024Q3
92
82.5
2.82
0.23
0.75
1.84
2.65
1.7%
2024Q2
91
78.7
2.81
0.29
0.78
1.74
2.79
0.1%
2024Q1
91
82.0
2.85
0.29
0.78
1.79
2.88
0.2%
2023Q4
92
82.0
2.82
0.22
0.80
1.80
2.86
0.8%
2023Q3
92
80.7
2.90
0.22
0.87
1.80
2.91
0.0%
2023Q2
91
82.7
2.92
0.23
0.83
1.86
2.93
14.8%
2023Q1
90
84.4
2.99
0.34
0.80
1.85
3.06
42.4%
2022Q4
92
80.8
2.95
0.39
0.76
1.80
2.96
60.4%
2022Q3
92
78.8
3.08
0.55
0.66
1.86
3.03
50.6%
2022Q2
91
80.8
3.35
0.55
0.53
2.27
2.98
40.7%
2022Q1
90
83.7
3.02
0.57
0.58
1.87
2.69
44.4%
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.
Provide appropriate treatment and care according to orders, resident’s preferences and goals.
D
2025-11-15
2025-07-24
Health
F0698
Provide safe, appropriate dialysis care/services for a resident who requires such services.
D
2025-08-21
2023-07-25
Health · complaint
F0684
Provide appropriate treatment and care according to orders, resident’s preferences and goals.
J
2023-07-13
2023-02-09
Health
F0693
Ensure that feeding tubes are not used unless there is a medical reason and the resident agrees; and provide appropriate care for a resident with a feeding tube.
D
2023-02-24
2023-02-09
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.
E
2023-02-24
2023-02-09
Health
F0867
Set up an ongoing quality assessment and assurance group to review quality deficiencies and develop corrective plans of action.
D
2023-02-24
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
10
Owner
Role
Pct
From
Status
Source
BYNC HOLDINGS LLC
5% OR GREATER DIRECT OWNERSHIP INTEREST
100%
2022-07-01
current
pecos_ownership
STARLIGHT HEALTHCARE LLC
5% OR GREATER INDIRECT OWNERSHIP INTEREST
50%
2022-07-01
current
pecos_ownership
CAPITAL HOLDINGS TRUST
5% OR GREATER INDIRECT OWNERSHIP INTEREST
47%
2022-07-01
current
pecos_ownership
JEREMIAS, BARUCH
CORPORATE DIRECTOR
—
2022-07-01
current
pecos_ownership
PITTMAN, CYNTHIA
W-2 MANAGING EMPLOYEE
—
2022-07-01
current
pecos_ownership
STERN, JACOB
CORPORATE DIRECTOR
—
2022-07-01
current
pecos_ownership
CYNTHIA PITTMAN
W-2 MANAGING EMPLOYEE
100%
2022-07-01
ended 2026-05-18
pecos_ownership
JACOB STERN
CORPORATE OFFICER
100%
2022-07-01
ended 2026-05-18
pecos_ownership
10-26 NATIONWIDE TR
5% OR GREATER INDIRECT OWNERSHIP INTEREST
50%
2022-07-01
ended 2026-05-18
pecos_ownership
BARUCH JEREMIAS
CORPORATE DIRECTOR
50%
2022-07-01
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
6
FY end
Total allowable
Rent
Home office
Therapy
Staffing
Counterparties
PropCo
2024-12-31
$694,821
—
$665,299
—
—
1
—
2023-12-31
$1,231,878
—
—
—
—
1
—
2022-12-31
$590,657
—
—
—
$238,457
1
—
2022-06-30
$188,655
—
$188,655
—
—
2
—
2022-03-31
$670,681
—
$670,681
—
—
2
—
2021-03-31
$665,087
—
$665,087
—
—
2
—
Cost-report related-party spend by fiscal year. has_propco flags real-estate counterparties.
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
36
Geo
Kind
BR
Amount
As of
Source
county 37025
acs median gross
0
$1,178
2024-12-31
CENSUS_ACS5
county 37025
fmr
0
$1,469
2025-10-01
HUD_USER_FMR
county 37025
acs median gross
1
$1,268
2024-12-31
CENSUS_ACS5
county 37025
fmr
1
$1,538
2025-10-01
HUD_USER_FMR
county 37025
acs median gross
2
$1,328
2024-12-31
CENSUS_ACS5
county 37025
fmr
2
$1,686
2025-10-01
HUD_USER_FMR
county 37025
acs median gross
3
$1,494
2024-12-31
CENSUS_ACS5
county 37025
fmr
3
$2,076
2025-10-01
HUD_USER_FMR
county 37025
acs median gross
4
$2,084
2024-12-31
CENSUS_ACS5
county 37025
fmr
4
$2,637
2025-10-01
HUD_USER_FMR
county 37025
acs median gross
5
$2,039
2024-12-31
CENSUS_ACS5
county 37025
acs median gross
$1,414
2024-12-31
CENSUS_ACS5
county 37025
acs recent mover gross
$1,809
2024-12-31
CENSUS_ACS5
zcta 28025
acs median gross
0
$1,115
2024-12-31
CENSUS_ACS5
zcta 28025
acs median gross
1
$890
2024-12-31
CENSUS_ACS5
zcta 28025
acs median gross
2
$1,107
2024-12-31
CENSUS_ACS5
zcta 28025
acs median gross
3
$1,342
2024-12-31
CENSUS_ACS5
zcta 28025
acs median gross
4
$1,839
2024-12-31
CENSUS_ACS5
zcta 28025
acs median gross
5
$1,776
2024-12-31
CENSUS_ACS5
zcta 28025
acs median gross
$1,244
2024-12-31
CENSUS_ACS5
zcta 28025
acs recent mover gross
$1,722
2024-12-31
CENSUS_ACS5
zip 28025
payment standard 110
0
$1,375
2025-10-01
HUD_USER_SAFMR
zip 28025
payment standard 90
0
$1,125
2025-10-01
HUD_USER_SAFMR
zip 28025
safmr
0
$1,250
2025-10-01
HUD_USER_SAFMR
zip 28025
payment standard 110
1
$1,441
2025-10-01
HUD_USER_SAFMR
zip 28025
payment standard 90
1
$1,179
2025-10-01
HUD_USER_SAFMR
zip 28025
safmr
1
$1,310
2025-10-01
HUD_USER_SAFMR
zip 28025
payment standard 110
2
$1,584
2025-10-01
HUD_USER_SAFMR
zip 28025
payment standard 90
2
$1,296
2025-10-01
HUD_USER_SAFMR
zip 28025
safmr
2
$1,440
2025-10-01
HUD_USER_SAFMR
zip 28025
payment standard 110
3
$1,947
2025-10-01
HUD_USER_SAFMR
zip 28025
payment standard 90
3
$1,593
2025-10-01
HUD_USER_SAFMR
zip 28025
safmr
3
$1,770
2025-10-01
HUD_USER_SAFMR
zip 28025
payment standard 110
4
$2,475
2025-10-01
HUD_USER_SAFMR
zip 28025
payment standard 90
4
$2,025
2025-10-01
HUD_USER_SAFMR
zip 28025
safmr
4
$2,250
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.