diff --git a/Makefile b/Makefile
index b03e23d55..47e3c5a74 100644
--- a/Makefile
+++ b/Makefile
@@ -60,6 +60,7 @@ database:
 	python policyengine_us_data/db/etl_medicaid.py
 	python policyengine_us_data/db/etl_snap.py
 	python policyengine_us_data/db/etl_irs_soi.py
+	python policyengine_us_data/db/scale_irs_soi_to_cbo.py
 	python policyengine_us_data/db/validate_database.py
 
 data:
diff --git a/policyengine_us_data/datasets/cps/cps.py b/policyengine_us_data/datasets/cps/cps.py
index f932e0d5e..ae9e37904 100644
--- a/policyengine_us_data/datasets/cps/cps.py
+++ b/policyengine_us_data/datasets/cps/cps.py
@@ -15,7 +15,6 @@
 from microimpute.models.qrf import QRF
 import logging
 
-
 test_lite = os.environ.get("TEST_LITE") == "true"
 print(f"TEST_LITE == {test_lite}")
 
diff --git a/policyengine_us_data/datasets/cps/enhanced_cps.py b/policyengine_us_data/datasets/cps/enhanced_cps.py
index 8bbe67bcc..4eb0a660b 100644
--- a/policyengine_us_data/datasets/cps/enhanced_cps.py
+++ b/policyengine_us_data/datasets/cps/enhanced_cps.py
@@ -22,7 +22,6 @@
 from pathlib import Path
 import logging
 
-
 try:
     import torch
 except ImportError:
diff --git a/policyengine_us_data/datasets/puf/puf.py b/policyengine_us_data/datasets/puf/puf.py
index cac9ad61a..7650d9e7f 100644
--- a/policyengine_us_data/datasets/puf/puf.py
+++ b/policyengine_us_data/datasets/puf/puf.py
@@ -15,7 +15,6 @@
     create_policyengine_uprating_factors_table,
 )
 
-
 rng = np.random.default_rng(seed=64)
 
 # Get Qualified Business Income simulation parameters ---
diff --git a/policyengine_us_data/datasets/puf/uprate_puf.py b/policyengine_us_data/datasets/puf/uprate_puf.py
index 1cf0eb9c6..961446156 100644
--- a/policyengine_us_data/datasets/puf/uprate_puf.py
+++ b/policyengine_us_data/datasets/puf/uprate_puf.py
@@ -2,7 +2,6 @@
 import numpy as np
 from policyengine_us_data.storage import STORAGE_FOLDER
 
-
 ITMDED_GROW_RATE = 0.02  # annual growth rate in itemized deduction amounts
 
 USE_VARIABLE_SPECIFIC_POPULATION_GROWTH_DIVISORS = False
diff --git a/policyengine_us_data/db/create_database_tables.py b/policyengine_us_data/db/create_database_tables.py
index df03772d0..920d1449e 100644
--- a/policyengine_us_data/db/create_database_tables.py
+++ b/policyengine_us_data/db/create_database_tables.py
@@ -15,7 +15,6 @@
 
 from policyengine_us_data.storage import STORAGE_FOLDER
 
-
 logging.basicConfig(
     level=logging.INFO,
     format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
diff --git a/policyengine_us_data/db/etl_age.py b/policyengine_us_data/db/etl_age.py
index bb83067c4..2f8b4b3df 100644
--- a/policyengine_us_data/db/etl_age.py
+++ b/policyengine_us_data/db/etl_age.py
@@ -11,7 +11,6 @@
 )
 from policyengine_us_data.utils.census import get_census_docs, pull_acs_table
 
-
 LABEL_TO_SHORT = {
     "Estimate!!Total!!Total population!!AGE!!Under 5 years": "0-4",
     "Estimate!!Total!!Total population!!AGE!!5 to 9 years": "5-9",
@@ -185,7 +184,7 @@ def load_age_data(df_long, geo, year, stratum_lookup=None):
 if __name__ == "__main__":
 
     # --- ETL: Extract, Transform, Load ----
-    year = 2023
+    year = 2024
 
     # ---- Extract ----------
     docs = get_census_docs(year)
diff --git a/policyengine_us_data/db/etl_irs_soi.py b/policyengine_us_data/db/etl_irs_soi.py
index 786abb1cc..6607a5dd6 100644
--- a/policyengine_us_data/db/etl_irs_soi.py
+++ b/policyengine_us_data/db/etl_irs_soi.py
@@ -24,7 +24,6 @@
     get_district_mapping,
 )
 
-
 """See the 22incddocguide.docx manual from the IRS SOI"""
 # Let's make this work with strict inequalities
 # Language in the doc: '$10,000 under $25,000'
diff --git a/policyengine_us_data/db/etl_medicaid.py b/policyengine_us_data/db/etl_medicaid.py
index 926a0d88c..e3d46d5c7 100644
--- a/policyengine_us_data/db/etl_medicaid.py
+++ b/policyengine_us_data/db/etl_medicaid.py
@@ -194,7 +194,7 @@ def load_medicaid_data(long_state, long_cd, year):
 
 if __name__ == "__main__":
 
-    year = 2023
+    year = 2024
 
     # Extract ------------------------------
     cd_survey_df, state_admin_df = extract_medicaid_data(year)
diff --git a/policyengine_us_data/db/etl_snap.py b/policyengine_us_data/db/etl_snap.py
index 1fba44a46..a39411ef5 100644
--- a/policyengine_us_data/db/etl_snap.py
+++ b/policyengine_us_data/db/etl_snap.py
@@ -20,7 +20,7 @@
 )
 
 
-def extract_administrative_snap_data(year=2023):
+def extract_administrative_snap_data(year=2024):
     """
     Downloads and extracts annual state-level SNAP data from the USDA FNS zip file.
     """
@@ -280,7 +280,7 @@ def load_survey_snap_data(survey_df, year, stratum_lookup=None):
 
 
 def main():
-    year = 2023
+    year = 2024
 
     # Extract ---------
     zip_file_admin = extract_administrative_snap_data()
diff --git a/policyengine_us_data/db/scale_irs_soi_to_cbo.py b/policyengine_us_data/db/scale_irs_soi_to_cbo.py
new file mode 100644
index 000000000..6d8cdccc9
--- /dev/null
+++ b/policyengine_us_data/db/scale_irs_soi_to_cbo.py
@@ -0,0 +1,230 @@
+"""Scale IRS SOI 2022 database targets to 2024 using CBO projections.
+
+The IRS SOI congressional-district data (22incd.csv) is the most recent
+available; 2023/2024 CD data has not been published yet.  To align the
+DB targets with the 2024 simulation year we scale each variable's
+aggregate to match the corresponding CBO / Treasury projection, using
+the same parameter values that the enhanced CPS calibration uses in
+loss.py.
+
+Only targets with source_id=5 (IRS SOI ETL) are affected.  Census,
+Medicaid, and SNAP targets already pull 2024 data directly from their
+administrative sources.
+
+See: https://github.com/PolicyEngine/policyengine-us-data/issues/503
+"""
+
+import logging
+from typing import Dict, Tuple
+
+from sqlalchemy import text
+from sqlmodel import Session, create_engine, select
+
+from policyengine_us.system import system
+from policyengine_us_data.storage import STORAGE_FOLDER
+from policyengine_us_data.db.create_database_tables import Target
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
+)
+logger = logging.getLogger(__name__)
+
+SOI_SOURCE_ID = 5
+SOI_YEAR = 2022
+TARGET_YEAR = 2024
+
+
+def _get_cbo_targets(year: int) -> Dict[str, float]:
+    """CBO / Treasury national totals for IRS SOI variables.
+
+    Mirrors the targets used in loss.py for enhanced CPS calibration.
+
+    Args:
+        year: Simulation year.
+
+    Returns:
+        Mapping of DB variable name to national total.
+    """
+    p = system.parameters(year)
+    cbo = p.calibration.gov.cbo
+    cbo_inc = cbo.income_by_source
+    soi = p.calibration.gov.irs.soi
+
+    # IRS SOI total returns (sum by filing status)
+    soi_total_returns = sum(
+        v
+        for v in soi.returns_by_filing_status._children.values()
+        if isinstance(v, (int, float))
+    )
+
+    return {
+        # CBO budget projections
+        "income_tax": cbo._children["income_tax"],
+        "unemployment_compensation": cbo._children[
+            "unemployment_compensation"
+        ],
+        # Treasury
+        "eitc": (
+            system.parameters.calibration.gov.treasury.tax_expenditures.eitc(
+                year
+            )
+        ),
+        # CBO income-by-source
+        "adjusted_gross_income": cbo_inc._children["adjusted_gross_income"],
+        "taxable_social_security": cbo_inc._children[
+            "taxable_social_security"
+        ],
+        "taxable_pension_income": cbo_inc._children["taxable_pension_income"],
+        "net_capital_gain": cbo_inc._children["net_capital_gain"],
+        # IRS SOI projections
+        "qualified_dividend_income": soi._children[
+            "qualified_dividend_income"
+        ],
+        "taxable_interest_income": soi._children["taxable_interest_income"],
+        "tax_exempt_interest_income": soi._children[
+            "tax_exempt_interest_income"
+        ],
+        "tax_unit_partnership_s_corp_income": soi._children[
+            "partnership_s_corp_income"
+        ],
+        "dividend_income": (
+            soi._children["qualified_dividend_income"]
+            + soi._children["non_qualified_dividend_income"]
+        ),
+        # Return counts
+        "person_count": soi_total_returns,
+    }
+
+
+def _compute_state_aggregate(
+    session: Session, variable: str
+) -> Tuple[float, int]:
+    """Sum state-level IRS SOI targets for *variable*.
+
+    Uses raw SQL to avoid the USVariable enum deserialization issue.
+
+    Args:
+        session: Active database session.
+        variable: Target variable name.
+
+    Returns:
+        (sum of state-level values, row count).
+    """
+    result = session.execute(
+        text("""
+            SELECT COALESCE(SUM(t.value), 0) AS total,
+                   COUNT(*)                  AS cnt
+            FROM   targets t
+            JOIN   stratum_constraints sc
+                   ON sc.stratum_id = t.stratum_id
+            WHERE  t.variable   = :variable
+               AND t.source_id  = :source_id
+               AND t.active     = 1
+               AND sc.constraint_variable = 'ucgid_str'
+               AND sc.value LIKE '0400000US%'
+            """),
+        {"variable": variable, "source_id": SOI_SOURCE_ID},
+    )
+    row = result.one()
+    return float(row.total), int(row.cnt)
+
+
+def _scale_targets(
+    session: Session,
+    variable: str,
+    scale_factor: float,
+    target_year: int,
+) -> int:
+    """Scale all IRS SOI targets for *variable* and update period.
+
+    Args:
+        session: Active database session.
+        variable: Target variable name.
+        scale_factor: Multiplicative adjustment.
+        target_year: New period value.
+
+    Returns:
+        Number of rows updated.
+    """
+    stmt = (
+        select(Target)
+        .where(Target.variable == variable)
+        .where(Target.source_id == SOI_SOURCE_ID)
+    )
+    all_targets = session.exec(stmt).all()
+
+    updated = 0
+    for t in all_targets:
+        if t.value is not None:
+            t.value *= scale_factor
+        t.period = target_year
+        session.add(t)
+        updated += 1
+
+    return updated
+
+
+def scale_soi_to_cbo(
+    session: Session,
+    target_year: int = TARGET_YEAR,
+) -> Dict[str, float]:
+    """Scale IRS SOI DB targets to CBO 2024 projections.
+
+    For each variable with a CBO/Treasury projection:
+    1. Sum current state-level DB targets.
+    2. Compute scale factor = CBO target / DB aggregate.
+    3. Apply proportionally to all geographic levels.
+
+    Args:
+        session: Active database session.
+        target_year: Simulation year.
+
+    Returns:
+        Mapping of variable name to scale factor applied.
+    """
+    cbo_targets = _get_cbo_targets(target_year)
+    scale_factors: Dict[str, float] = {}
+
+    for variable, cbo_value in cbo_targets.items():
+        state_sum, state_count = _compute_state_aggregate(session, variable)
+
+        if state_sum == 0:
+            logger.warning(
+                "Skipping '%s': no state-level SOI targets",
+                variable,
+            )
+            continue
+
+        scale = cbo_value / state_sum
+        pct = (scale - 1) * 100
+
+        logger.info(
+            "%-35s  %4d states  %.3g -> %.3g  " "(x%.4f, %+.1f%%)",
+            variable,
+            state_count,
+            state_sum,
+            cbo_value,
+            scale,
+            pct,
+        )
+
+        n = _scale_targets(session, variable, scale, target_year)
+        logger.info("  Updated %d rows", n)
+        scale_factors[variable] = scale
+
+    session.commit()
+    logger.info("IRS SOI -> CBO scaling complete.")
+    return scale_factors
+
+
+def main() -> None:
+    db_url = f"sqlite:///{STORAGE_FOLDER / 'policy_data.db'}"
+    engine = create_engine(db_url)
+
+    with Session(engine) as session:
+        scale_soi_to_cbo(session)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/policyengine_us_data/db/validate_database.py b/policyengine_us_data/db/validate_database.py
index fee6a49dc..53ac09852 100644
--- a/policyengine_us_data/db/validate_database.py
+++ b/policyengine_us_data/db/validate_database.py
@@ -9,7 +9,6 @@
 import pandas as pd
 from policyengine_us.system import system
 
-
 conn = sqlite3.connect("policyengine_us_data/storage/policy_data.db")
 
 stratum_constraints_df = pd.read_sql("SELECT * FROM stratum_constraints", conn)
diff --git a/policyengine_us_data/storage/calibration_targets/pull_snap_targets.py b/policyengine_us_data/storage/calibration_targets/pull_snap_targets.py
index 349e6fbdd..1830bdb3a 100644
--- a/policyengine_us_data/storage/calibration_targets/pull_snap_targets.py
+++ b/policyengine_us_data/storage/calibration_targets/pull_snap_targets.py
@@ -9,7 +9,6 @@
     STATE_NAME_TO_ABBREV,
 )
 
-
 STATE_NAME_TO_FIPS = {
     "Alabama": "01",
     "Alaska": "02",
diff --git a/policyengine_us_data/tests/test_datasets/test_county_fips.py b/policyengine_us_data/tests/test_datasets/test_county_fips.py
index ad1f10c5c..d692cf559 100644
--- a/policyengine_us_data/tests/test_datasets/test_county_fips.py
+++ b/policyengine_us_data/tests/test_datasets/test_county_fips.py
@@ -10,7 +10,6 @@
     LOCAL_FOLDER,
 )
 
-
 # Sample data that mimics the format from census.gov
 SAMPLE_CENSUS_DATA = """STATE|STATEFP|COUNTYFP|COUNTYNAME
 AL|01|001|Autauga County
diff --git a/policyengine_us_data/tests/test_scale_irs_soi_to_cbo.py b/policyengine_us_data/tests/test_scale_irs_soi_to_cbo.py
new file mode 100644
index 000000000..b947723e1
--- /dev/null
+++ b/policyengine_us_data/tests/test_scale_irs_soi_to_cbo.py
@@ -0,0 +1,137 @@
+"""Tests for CBO-based scaling of IRS SOI database targets."""
+
+import pytest
+from sqlmodel import Session, select
+
+from policyengine_us_data.db.create_database_tables import (
+    Stratum,
+    StratumConstraint,
+    Target,
+    create_database,
+)
+from policyengine_us_data.db.scale_irs_soi_to_cbo import (
+    SOI_SOURCE_ID,
+    TARGET_YEAR,
+    _compute_state_aggregate,
+    _get_cbo_targets,
+    _scale_targets,
+    scale_soi_to_cbo,
+)
+
+
+@pytest.fixture
+def engine(tmp_path):
+    db_uri = f"sqlite:///{tmp_path / 'test.db'}"
+    return create_database(db_uri)
+
+
+def _make_stratum(session, ucgid):
+    """Helper: create a stratum with a ucgid_str constraint."""
+    s = Stratum(stratum_group_id=0, notes=f"Geo: {ucgid}")
+    s.constraints_rel = [
+        StratumConstraint(
+            constraint_variable="ucgid_str",
+            operation="in",
+            value=ucgid,
+        )
+    ]
+    session.add(s)
+    session.flush()
+    return s
+
+
+CBO_VARIABLES = [
+    "income_tax",
+    "unemployment_compensation",
+    "eitc",
+    "adjusted_gross_income",
+    "taxable_social_security",
+    "taxable_pension_income",
+    "net_capital_gain",
+    "qualified_dividend_income",
+    "taxable_interest_income",
+    "tax_exempt_interest_income",
+    "tax_unit_partnership_s_corp_income",
+    "dividend_income",
+    "person_count",
+]
+
+
+def test_cbo_targets_are_positive():
+    """All CBO targets return positive 2024 values."""
+    targets = _get_cbo_targets(TARGET_YEAR)
+    for name in CBO_VARIABLES:
+        assert name in targets, f"'{name}' missing"
+        assert targets[name] > 0, f"{name} = {targets[name]}"
+
+
+def test_only_soi_targets_are_scaled(engine):
+    """Scaling only affects source_id=5, not other sources."""
+    with Session(engine) as session:
+        st = _make_stratum(session, "0400000US06")
+        st.targets_rel = [
+            Target(
+                variable="income_tax",
+                period=2022,
+                value=300e9,
+                source_id=SOI_SOURCE_ID,
+                active=True,
+            ),
+        ]
+        st2 = _make_stratum(session, "0400000US48")
+        st2.targets_rel = [
+            Target(
+                variable="person_count",
+                period=2023,
+                value=30_000_000,
+                source_id=1,  # Census age, not SOI
+                active=True,
+            ),
+        ]
+        session.commit()
+
+        _scale_targets(session, "income_tax", 1.5, 2024)
+        session.commit()
+
+        soi_t = session.exec(
+            select(Target)
+            .where(Target.variable == "income_tax")
+            .where(Target.source_id == SOI_SOURCE_ID)
+        ).one()
+        assert soi_t.value == pytest.approx(450e9)
+        assert soi_t.period == 2024
+
+        census_t = session.exec(
+            select(Target)
+            .where(Target.variable == "person_count")
+            .where(Target.source_id == 1)
+        ).one()
+        assert census_t.value == pytest.approx(30_000_000)
+        assert census_t.period == 2023
+
+
+def test_end_to_end_scaling(engine):
+    """After scaling, state aggregate matches CBO target."""
+    cbo = _get_cbo_targets(TARGET_YEAR)
+    cbo_income_tax = cbo["income_tax"]
+
+    with Session(engine) as session:
+        for fips, share in [("01", 0.02), ("06", 0.15), ("48", 0.10)]:
+            val = cbo_income_tax * share * 0.5  # intentionally stale
+            st = _make_stratum(session, f"0400000US{fips}")
+            st.targets_rel = [
+                Target(
+                    variable="income_tax",
+                    period=2022,
+                    value=val,
+                    source_id=SOI_SOURCE_ID,
+                    active=True,
+                )
+            ]
+        session.commit()
+
+        factors = scale_soi_to_cbo(session, TARGET_YEAR)
+
+        assert "income_tax" in factors
+        new_total, _ = _compute_state_aggregate(session, "income_tax")
+        assert new_total == pytest.approx(cbo_income_tax, rel=1e-6)
diff --git a/policyengine_us_data/utils/census.py b/policyengine_us_data/utils/census.py
index 2f424ccb8..8081b6162 100644
--- a/policyengine_us_data/utils/census.py
+++ b/policyengine_us_data/utils/census.py
@@ -4,7 +4,6 @@
 import pandas as pd
 import numpy as np
 
-
 STATE_NAME_TO_FIPS = {
     "Alabama": "01",
     "Alaska": "02",
diff --git a/policyengine_us_data/utils/huggingface.py b/policyengine_us_data/utils/huggingface.py
index 7b8c07928..d9b2f8a51 100644
--- a/policyengine_us_data/utils/huggingface.py
+++ b/policyengine_us_data/utils/huggingface.py
@@ -1,7 +1,6 @@
 from huggingface_hub import hf_hub_download, login, HfApi
 import os
 
-
 TOKEN = os.environ.get("HUGGING_FACE_TOKEN")
 if not TOKEN:
     raise ValueError(
diff --git a/policyengine_us_data/utils/loss.py b/policyengine_us_data/utils/loss.py
index cbea6dabb..e368d5048 100644
--- a/policyengine_us_data/utils/loss.py
+++ b/policyengine_us_data/utils/loss.py
@@ -9,7 +9,6 @@
 from policyengine_core.reforms import Reform
 from policyengine_us_data.utils.soi import pe_to_soi, get_soi
 
-
 # CPS-derived statistics
 # Medical expenses, sum of spm thresholds
 # Child support expenses