Add JCT tax expenditure source package

Author: MaxGhenis

arch/source_package.py

@@ -86,17 +86,11 @@
     "census-acs-s2201-congressional-district-snap-2024": Path(
         "census/acs_s2201_district_2024"
     ),
-    "census-b01001-female-age-2023": Path(
-        "census/b01001_female_15_44_2023"
-    ),
+    "census-b01001-female-age-2023": Path("census/b01001_female_15_44_2023"),
     "census-pep-2024-national-age-sex": Path("census/pep_2024_national_age_sex"),
     "census-pep-2024-state-age-sex": Path("census/pep_2024_state_age_sex"),
-    "census-population-projections-2023": Path(
-        "census/population_projections_2023"
-    ),
-    "census-stc-individual-income-tax": Path(
-        "census/stc_individual_income_tax"
-    ),
+    "census-population-projections-2023": Path("census/population_projections_2023"),
+    "census-stc-individual-income-tax": Path("census/stc_individual_income_tax"),
     "cms-medicaid-chip-monthly-enrollment-december-2024": Path(
         "cms_medicaid/chip_monthly_enrollment_december_2024"
     ),
@@ -106,9 +100,7 @@
     "cms-aca-oep-state-level": Path("cms_aca/oep_state_level"),
     "cms-aca-oep-state-level-2022": Path("cms_aca/oep_state_level_2022"),
     "cms-aca-oep-state-level-2025": Path("cms_aca/oep_state_level_2025"),
-    "cms-aca-effectuated-enrollment-2022": Path(
-        "cms_aca/effectuated_enrollment_2022"
-    ),
+    "cms-aca-effectuated-enrollment-2022": Path("cms_aca/effectuated_enrollment_2022"),
     "cms-medicare-trustees-report-2025-part-b-premium-income": Path(
         "cms_medicare/medicare_trustees_report_2025"
     ),
@@ -122,6 +114,7 @@
     "hhs-acf-liheap-fy2024-national-profile": Path(
         "hhs_acf_liheap/fy2024_national_profile"
     ),
+    "jct-tax-expenditures-2024": Path("jct/tax_expenditures_2024"),
     "soi-table-1-1": Path("irs_soi/table_1_1"),
     "soi-table-1-2": Path("irs_soi/table_1_2"),
     "soi-table-1-4": Path("irs_soi/table_1_4"),
@@ -132,9 +125,7 @@
     ),
     "soi-table-4-3": Path("irs_soi/table_4_3"),
     "soi-state-2022": Path("irs_soi/state_2022"),
-    "soi-congressional-district-2022": Path(
-        "irs_soi/congressional_district_2022"
-    ),
+    "soi-congressional-district-2022": Path("irs_soi/congressional_district_2022"),
     "soi-historic-table-2": Path("irs_soi/historic_table_2"),
     "soi-historic-table-2-state-agi-2022": Path(
         "irs_soi/historic_table_2_state_agi_2022"

db/data/jct/tax_expenditures_2024/jct_tax_expenditures_2024.csv

@@ -0,0 +1,6 @@
+tax_expenditure,label,jct_line_label,individual_revenue_loss_2024,definition_note
+salt_deduction,State and local tax deduction,Taxes paid deduction,21700000000,Individual income tax revenue loss for itemized state and local tax deduction.
+medical_expense_deduction,Medical expense deduction,Medical expenses deduction,11400000000,Individual income tax revenue loss for itemized medical expense deduction.
+charitable_deduction,Charitable contribution deduction,"Charitable contributions, other than education and health; charitable contributions, education; charitable contributions, health",60400000000,Sum of individual income tax revenue-loss rows for charitable contributions excluding corporate income tax estimates.
+deductible_mortgage_interest,Deductible mortgage interest,Deductibility of mortgage interest on owner-occupied homes,24800000000,Individual income tax revenue loss for deductible mortgage interest on owner-occupied homes.
+qualified_business_income_deduction,Qualified business income deduction,20-percent deduction for qualified business income,63100000000,Individual income tax revenue loss for qualified business income deduction.

db/data/jct/tax_expenditures_2024/manifest.yaml

@@ -0,0 +1,30 @@
+id: jct-tax-expenditures-2024
+title: JCT Estimates of Federal Tax Expenditures for Fiscal Years 2024-2028
+publisher: Joint Committee on Taxation
+description: >
+  Selected calendar-year 2024 individual income tax revenue-loss estimates from
+  JCX-48-24 Table 1, curated for Populace fiscal calibration targets that must be
+  encoded as simple reforms rather than static PolicyEngine variables.
+source_page: https://www.jct.gov/publications/2024/jcx-48-24/
+source_url: https://www.jct.gov/getattachment/765709fb-9a4b-430a-8f9e-4d342ec97f7e/x-48-24.pdf
+retrieved_at: "2026-06-16T00:00:00Z"
+license: public-domain
+files:
+  2024:
+    filename: jct_tax_expenditures_2024.csv
+    source_url: https://www.jct.gov/getattachment/765709fb-9a4b-430a-8f9e-4d342ec97f7e/x-48-24.pdf
+    sha256: a6db137830f744ef140c796e23da2673480a70fb3fbcba848476d5ccbf27ffa8
+    size_bytes: 1154
+    source_table: Estimates of Federal Tax Expenditures for Fiscal Years 2024-2028
+    year: 2024
+    storage:
+      r2:
+        provider: r2
+        bucket: arch-raw
+        key: raw/jct/jct-tax-expenditures-2024/2024/a6db137830f744ef140c796e23da2673480a70fb3fbcba848476d5ccbf27ffa8/jct_tax_expenditures_2024.csv
+        uri: r2://arch-raw/raw/jct/jct-tax-expenditures-2024/2024/a6db137830f744ef140c796e23da2673480a70fb3fbcba848476d5ccbf27ffa8/jct_tax_expenditures_2024.csv
+notes:
+  - >
+    Calendar-year 2024 values use the individual income tax revenue-loss column
+    only. For charitable contributions, the value sums the three individual
+    charitable rows and excludes corporate revenue-loss columns.

packages/jct/tax_expenditures_2024/source_package.yaml

@@ -0,0 +1,114 @@
+schema_version: arch.source_package.v1
+package_id: jct-tax-expenditures-2024
+label: JCT 2024 individual income tax expenditure estimates
+artifact:
+  source_name: jct
+  source_table: Estimates of Federal Tax Expenditures for Fiscal Years 2024-2028
+  resource_package: db
+  resource_directory: data/jct/tax_expenditures_2024
+  manifest: manifest.yaml
+  vintage: jcx_48_24
+  extracted_at: "2026-06-16"
+  extraction_method: manual extraction from JCX-48-24 Table 1 individual income tax revenue-loss columns
+  parser: delimited_text_full_rows
+  sheet_name: jct_tax_expenditures_2024
+record_sets:
+  - record_set_id: jct.tax_expenditures.cy2024
+    record_set_spec_id: jct.individual_tax_expenditure_revenue_loss.v1
+    source_record_id_prefix: jct.tax_expenditures.cy2024
+    sheet_name: jct_tax_expenditures_2024
+    period_type: calendar_year
+    period: 2024
+    geography_id: 0100000US
+    geography_level: country
+    geography_name: United States
+    geography_vintage: current
+    entity: tax_unit
+    entity_role: federal_income_tax_unit
+    domain: federal_income_tax
+    groupby_dimension: jct.tax_expenditure
+    rows:
+      - value_id: salt_deduction
+        label: State and local tax deduction
+        ordinal: 0
+        row_number: 2
+        expected_row_header_column: A
+        expected_row_header: salt_deduction
+        filters:
+          tax_expenditure: salt_deduction
+        constraints:
+          - variable: tax_expenditure
+            operator: "=="
+            value: salt_deduction
+            label: JCT tax expenditure row
+        table_record_kind: total
+      - value_id: medical_expense_deduction
+        label: Medical expense deduction
+        ordinal: 1
+        row_number: 3
+        expected_row_header_column: A
+        expected_row_header: medical_expense_deduction
+        filters:
+          tax_expenditure: medical_expense_deduction
+        constraints:
+          - variable: tax_expenditure
+            operator: "=="
+            value: medical_expense_deduction
+            label: JCT tax expenditure row
+        table_record_kind: total
+      - value_id: charitable_deduction
+        label: Charitable contribution deduction
+        ordinal: 2
+        row_number: 4
+        expected_row_header_column: A
+        expected_row_header: charitable_deduction
+        filters:
+          tax_expenditure: charitable_deduction
+        constraints:
+          - variable: tax_expenditure
+            operator: "=="
+            value: charitable_deduction
+            label: JCT tax expenditure row
+        table_record_kind: total
+      - value_id: deductible_mortgage_interest
+        label: Deductible mortgage interest
+        ordinal: 3
+        row_number: 5
+        expected_row_header_column: A
+        expected_row_header: deductible_mortgage_interest
+        filters:
+          tax_expenditure: deductible_mortgage_interest
+        constraints:
+          - variable: tax_expenditure
+            operator: "=="
+            value: deductible_mortgage_interest
+            label: JCT tax expenditure row
+        table_record_kind: total
+      - value_id: qualified_business_income_deduction
+        label: Qualified business income deduction
+        ordinal: 4
+        row_number: 6
+        expected_row_header_column: A
+        expected_row_header: qualified_business_income_deduction
+        filters:
+          tax_expenditure: qualified_business_income_deduction
+        constraints:
+          - variable: tax_expenditure
+            operator: "=="
+            value: qualified_business_income_deduction
+            label: JCT tax expenditure row
+        table_record_kind: total
+    measures:
+      - measure_id: revenue_loss
+        label: Individual income tax revenue loss
+        ordinal: 0
+        column: D
+        source_column_id: individual_revenue_loss_2024
+        expected_column_header_row: 1
+        expected_column_header: individual_revenue_loss_2024
+        concept: jct.individual_tax_expenditure_revenue_loss
+        source_concept: jct.individual_income_tax_revenue_loss
+        concept_relation: source_label
+        unit: usd
+        aggregation: sum
+        expected_cell_type: number

tests/test_arch_bundle.py

@@ -16,9 +16,7 @@ def test_build_bundle_writes_merged_consumer_contract(tmp_path):
     output_dir = tmp_path / "bundle"
 
     report = build_bundle(output_dir, year=2023)
-    summary = json.loads(
-        (output_dir / "reports" / "build_bundle.json").read_text()
-    )
+    summary = json.loads((output_dir / "reports" / "build_bundle.json").read_text())
     rows = _load_jsonl(output_dir / "consumer_facts.jsonl")
     source_packages = json.loads((output_dir / "source_packages.json").read_text())
     coverage = json.loads((output_dir / "coverage.json").read_text())
@@ -144,11 +142,7 @@ def test_build_bundle_writes_merged_consumer_contract(tmp_path):
     ]
     assert (output_dir / "sources" / "soi-table-1-1" / "consumer_facts.jsonl").exists()
     assert (
-        output_dir
-        / "sources"
-        / "soi-table-1-4"
-        / "reports"
-        / "build_summary.json"
+        output_dir / "sources" / "soi-table-1-4" / "reports" / "build_summary.json"
     ).exists()
     assert (
         output_dir
@@ -163,7 +157,10 @@ def test_build_bundle_writes_merged_consumer_contract(tmp_path):
         / "consumer_facts.jsonl"
     ).exists()
     assert (
-        output_dir / "sources" / "census-stc-individual-income-tax" / "consumer_facts.jsonl"
+        output_dir
+        / "sources"
+        / "census-stc-individual-income-tax"
+        / "consumer_facts.jsonl"
     ).exists()
     assert (
         output_dir
@@ -294,10 +291,7 @@ def test_build_bundle_cli_supports_ssa_supplement_source(tmp_path, capsys):
     assert payload["counts"]["fact_count"] == 6
     assert payload["coverage"]["counts"]["by_source"] == {"ssa": 6}
     assert payload["coverage"]["counts"]["by_entity"] == {"person": 6}
-    assert {
-        row["universe_constraints"]["constraints"][0]["value"]
-        for row in rows
-    } == {
+    assert {row["universe_constraints"]["constraints"][0]["value"] for row in rows} == {
         "social_security_benefits",
         "social_security_retirement_benefits",
         "social_security_survivors_benefits",
@@ -307,6 +301,38 @@ def test_build_bundle_cli_supports_ssa_supplement_source(tmp_path, capsys):
     }
 
 
+def test_build_bundle_cli_supports_jct_tax_expenditure_source(tmp_path, capsys):
+    output_dir = tmp_path / "bundle"
+
+    exit_code = harness_main(
+        [
+            "build-bundle",
+            "--year",
+            "2024",
+            "--source",
+            "jct-tax-expenditures-2024",
+            "--out",
+            str(output_dir),
+        ]
+    )
+    payload = json.loads(capsys.readouterr().out)
+    rows = _load_jsonl(output_dir / "consumer_facts.jsonl")
+
+    assert exit_code == 0
+    assert payload["valid"]
+    assert payload["counts"]["source_package_count"] == 1
+    assert payload["counts"]["fact_count"] == 5
+    assert payload["coverage"]["counts"]["by_source"] == {"jct": 5}
+    assert payload["coverage"]["counts"]["by_entity"] == {"tax_unit": 5}
+    assert {row["lineage"]["source_record_id"] for row in rows} == {
+        "jct.tax_expenditures.cy2024.salt_deduction.revenue_loss",
+        "jct.tax_expenditures.cy2024.medical_expense_deduction.revenue_loss",
+        "jct.tax_expenditures.cy2024.charitable_deduction.revenue_loss",
+        "jct.tax_expenditures.cy2024.deductible_mortgage_interest.revenue_loss",
+        "jct.tax_expenditures.cy2024.qualified_business_income_deduction.revenue_loss",
+    }
+
+
 def test_build_bundle_coverage_reports_duplicate_keys():
     rows = [
         {