Merge pull request 'feat: coverage argument + always-on reporting-coverage metadata (#13)' (#24) from feat/coverage-disclosure-13 into main

NEWS.md

@@ -1,5 +1,39 @@
 # uscogdata 0.1.0 (development)
 
+## Multi-government aggregates now disclose their reporting coverage
+
+* The Census of Governments is a **complete census only in years ending in 2
+  and 7**; every other year is a sample, and the sample varies enormously. On
+  the bundled fixture, Wisconsin's 608-city universe rolls up **597**
+  governments in FY2012 and **112** in FY2019 — an 18%-to-98% swing the
+  return value said nothing about, so a statewide total resting on a fifth of
+  the universe looked exactly like one resting on all of it.
+* `cog_geographic_rollup()`, `cog_peer_compare()` and `cog_find_peers()` gain
+  `coverage`:
+
+  | value | effect |
+  |---|---|
+  | `"all"` (default) | every unit that reported that year — unchanged behaviour |
+  | `"census"` | census years only; aborts if the range holds none rather than returning nothing |
+  | `"consistent"` | only units reporting in *every* requested year — a balanced panel |
+
+* **Regardless of mode**, every result now carries `provenance$coverage` with
+  per-year `n_units_reporting`, `n_units_expected` and `is_census_year`, plus
+  `provenance$coverage_mode`. `cog_explain()` prints a "Reporting coverage"
+  section. So the default mode can no longer mislead silently.
+* `is_census_year` is a statement about the **survey calendar**, never a claim
+  of completeness: FY1967 is a census year in which only 97 of Wisconsin's 608
+  cities report. `n_units_reporting` is the number that tells the truth.
+* On `cog_peer_compare()` the target is exempt from `"consistent"` balancing —
+  it is the subject of the comparison, not a member of the cohort — and the
+  `summary_*` quantiles are computed after the filter, so they describe the
+  cohort actually returned. `n_units_reporting` counts peers only, against the
+  cohort size.
+* On `cog_find_peers()`, `coverage` governs the cohort **vintage** when `year`
+  is `NULL`: `"census"` snaps to the most recent census year with an observed
+  population, so a cohort is not built from a sample year in which most of the
+  candidate universe is absent.
+
 ## `complete = TRUE`: absent cells, labelled with why they are absent
 
 * `cog_spending()` and `cog_revenue()` gain `complete`, defaulting to `FALSE`

R/coverage.R

@@ -0,0 +1,107 @@
+# R/coverage.R
+#
+# Reporting-coverage disclosure for the multi-government verbs (uscogdata#13,
+# findings F-020 and F-023).
+#
+# The Census of Governments is a COMPLETE CENSUS only in years ending in 2 and
+# 7. Every other year is a sample, and the sample varies enormously: on the
+# bundled fixture, Wisconsin's 608-city universe reports 597 governments in
+# FY2012 and 112 in FY2019. Summing "whatever reported" across those years is
+# what the verbs have always done -- correctly -- but the return value said
+# nothing about it, so a statewide total resting on 18% of the universe looked
+# exactly like one resting on 98%.
+#
+# Owner's settled design: a `coverage` argument selecting WHICH units to
+# include, plus always-on metadata saying how many there were either way. The
+# principle behind it: using these verbs correctly must not require the caller
+# to know the survey calendar.
+
+# Years ending in 2 or 7 are full censuses of every government; all others are
+# samples.
+.CENSUS_YEAR_ENDINGS <- c(2L, 7L)
+
+#' @noRd
+.is_census_year <- function(years) {
+  as.integer(years) %% 10L %in% .CENSUS_YEAR_ENDINGS
+}
+
+#' @noRd
+.validate_coverage <- function(coverage) {
+  tryCatch(
+    match.arg(coverage, c("all", "census", "consistent")),
+    error = function(e) {
+      cli::cli_abort(
+        "`coverage` must be one of {.val all}, {.val census} or {.val consistent}.",
+        class = "uscogdata_invalid_coverage", parent = e
+      )
+    }
+  )
+}
+
+#' Restrict `years` to census years for `coverage = "census"`.
+#'
+#' Aborts rather than returning an empty result when the requested range holds
+#' no census year: silently handing back zero rows for a query the caller
+#' believes they made is the failure mode this whole issue is about.
+#' @noRd
+.apply_census_years <- function(years, coverage, verb) {
+  if (!identical(coverage, "census")) return(as.integer(years))
+  keep <- as.integer(years)[.is_census_year(years)]
+  if (length(keep) == 0L) {
+    cli::cli_abort(c(
+      "{.code coverage = \"census\"} leaves no years to query.",
+      x = "None of the requested years end in 2 or 7: {.val {sort(unique(as.integer(years)))}}.",
+      i = "Census of Governments years ending in 2 or 7 are complete censuses; all others are samples.",
+      i = "Use {.code coverage = \"all\"} (the default) to keep every requested year, or request a census year."
+    ), class = "uscogdata_no_census_years")
+  }
+  sort(keep)
+}
+
+#' Keep only units that report in EVERY requested year (a balanced panel).
+#'
+#' `id_col` is the government identifier; `keep_ids` are rows exempt from the
+#' filter (the peer-comparison target, which is the subject of the comparison
+#' rather than a member of the cohort being balanced).
+#' @noRd
+.filter_consistent <- function(result, years, id_col = "canonical_govid",
+                               keep_ids = character(0)) {
+  years <- unique(as.integer(years))
+  if (nrow(result) == 0L || length(years) <= 1L) return(result)
+  ids <- setdiff(unique(result[[id_col]]), c(NA, keep_ids))
+  present <- vapply(ids, function(g) {
+    all(years %in% unique(as.integer(result$year[result[[id_col]] == g])))
+  }, logical(1))
+  consistent <- c(ids[present], keep_ids)
+  result[result[[id_col]] %in% consistent | is.na(result[[id_col]]), ,
+         drop = FALSE]
+}
+
+#' Per-year coverage metadata, always attached regardless of mode.
+#'
+#' Built from the REQUESTED years rather than the years present in the result,
+#' so a year in which nothing reported still appears -- with
+#' `n_units_reporting = 0`, which is precisely the disclosure a silently
+#' missing year fails to make.
+#'
+#' `n_units_reporting` describes the result the caller actually received, so
+#' under `coverage = "consistent"` it reports the balanced count. `is_census_year`
+#' is a statement about the SURVEY CALENDAR, never a claim of completeness:
+#' FY1967 is a census year in which only 97 of Wisconsin's 608 cities report.
+#' `n_units_reporting` is the number that tells the truth.
+#' @noRd
+.coverage_table <- function(result, years, n_expected,
+                            id_col = "canonical_govid", rows = NULL) {
+  years <- sort(unique(as.integer(years)))
+  src <- if (is.null(rows)) result else rows
+  reporting <- vapply(years, function(y) {
+    ids <- src[[id_col]][as.integer(src$year) == y]
+    length(unique(ids[!is.na(ids)]))
+  }, integer(1))
+  tibble::tibble(
+    year              = years,
+    n_units_reporting = as.integer(reporting),
+    n_units_expected  = rep(as.integer(n_expected), length(years)),
+    is_census_year    = .is_census_year(years)
+  )
+}

R/explain.R

@@ -118,6 +118,23 @@ cog_explain <- function(result, format = c("print", "list")) {
     cli::cli_ul(sugg_lines)
   }
 
+  if (!is.null(prov$coverage) && nrow(prov$coverage) > 0L) {
+    cli::cli_h2("Reporting coverage")
+    cli::cli_text("Mode: {prov$coverage_mode %||% 'all'}")
+    cov <- prov$coverage
+    cli::cli_ul(sprintf(
+      "%d: %d of %d units reporting (%.0f%%) -- %s year",
+      cov$year, cov$n_units_reporting, cov$n_units_expected,
+      100 * cov$n_units_reporting / pmax(cov$n_units_expected, 1L),
+      ifelse(cov$is_census_year, "census", "sample")
+    ))
+    if (any(!cov$is_census_year)) {
+      cli::cli_text(
+        "Note: the Census of Governments is a complete census only in years ending in 2 or 7; every other year is a sample."
+      )
+    }
+  }
+
   if (isTRUE(prov$completion$applied)) {
     cli::cli_h2("Completion")
     cli::cli_text(

R/peers.R

@@ -19,6 +19,13 @@
 #'   target's population at `year` to produce absolute bounds. If `FALSE`,
 #'   `pop_range` is interpreted as absolute population counts.
 #' @param max_peers Integer cap on the number of peers returned.
+#' @param coverage Survey-cycle handling; see [cog_peer_compare()]. Here it
+#'   governs the cohort VINTAGE when `year` is `NULL`: `"census"` snaps to the
+#'   most recent census year with an observed population, so a cohort is not
+#'   built from a sample year in which most of the candidate universe is
+#'   absent. `"consistent"` needs a year range, which cohort selection does not
+#'   have, so it selects like `"all"` and is carried on the result as
+#'   `attr(x, "coverage")` for [cog_peer_compare()].
 #' @return Tibble with columns `canonical_govid`, `gov_name`, `fips_state`,
 #'   `population`, `pop_ratio`, `rank`. The cohort year is attached as
 #'   `attr(x, "cohort_year")`.
@@ -29,7 +36,9 @@ cog_find_peers <- function(target_govid,
                            same_state = FALSE,
                            pop_range = c(0.7, 1.3),
                            is_ratio = TRUE,
-                           max_peers = 10L) {
+                           max_peers = 10L,
+                           coverage = c("all", "census", "consistent")) {
+  coverage <- .validate_coverage(coverage)
   if (!is.character(target_govid) || length(target_govid) != 1L) {
     cli::cli_abort("`target_govid` must be a length-1 character string.")
   }
@@ -59,7 +68,7 @@ cog_find_peers <- function(target_govid,
     ))
   }
 
-  cohort_year <- .resolve_cohort_year(con, target_govid, year)
+  cohort_year <- .resolve_cohort_year(con, target_govid, year, coverage)
 
   pop_sql <- sprintf(
     "SELECT population FROM gov_population_yearly
@@ -107,12 +116,34 @@ cog_find_peers <- function(target_govid,
   attr(peers, "cohort_year") <- as.integer(cohort_year)
   attr(peers, "pop_range")   <- as.numeric(pop_range)
   attr(peers, "is_ratio")    <- isTRUE(is_ratio)
+  attr(peers, "coverage")    <- coverage
+  attr(peers, "is_census_year") <- .is_census_year(cohort_year)
   peers
 }
 
+# `coverage` picks the cohort vintage when the caller did not name one.
+# "census" snaps to the most recent CENSUS year with an observed population,
+# so a cohort is not silently built from a sample year in which most of the
+# candidate universe is absent. "consistent" is a comparison-time concept --
+# it needs a year RANGE, which cohort selection does not have -- so it selects
+# like "all" here and is carried on the result for cog_peer_compare().
 #' @noRd
-.resolve_cohort_year <- function(con, target_govid, year) {
+.resolve_cohort_year <- function(con, target_govid, year,
+                                 coverage = "all") {
   if (!is.null(year)) return(as.integer(year))
+  if (identical(coverage, "census")) {
+    sql <- sprintf(
+      "SELECT MAX(year) AS y FROM gov_population_yearly
+       WHERE canonical_govid = %s AND year %% 10 IN (2, 7)",
+      .sql_lit_chr(target_govid)
+    )
+    y <- DBI::dbGetQuery(con, sql)$y
+    if (length(y) > 0L && !is.na(y)) return(as.integer(y))
+    cli::cli_abort(c(
+      "{.code coverage = \"census\"} found no census year with an observed population for {target_govid}.",
+      i = "Pass an explicit {.arg year}, or use {.code coverage = \"all\"}."
+    ), class = "uscogdata_no_census_years")
+  }
   sql <- sprintf(
     "SELECT MAX(year) AS y FROM gov_population_yearly
      WHERE canonical_govid = %s",
@@ -149,6 +180,31 @@ cog_find_peers <- function(target_govid,
 #'   `"direct"` is accepted; the `"total"` option exists in [cog_spending()] for
 #'   single-government queries but cannot be used here because combining Total
 #'   across peer sets counts intergovernmental transfers twice.
+#' @param coverage How to handle the Census of Governments survey cycle,
+#'   which is a **complete census only in years ending in 2 and 7** -- every
+#'   other year is a sample, and the sample varies enormously (on the bundled
+#'   fixture, Wisconsin's 608-city universe reports 597 governments in FY2012
+#'   and 112 in FY2019).
+#'
+#'   * `"all"` (default) -- every unit that reported that year. Unchanged
+#'     behaviour, so existing code keeps working.
+#'   * `"census"` -- census years only. Aborts if the requested range holds
+#'     none, rather than silently returning nothing.
+#'   * `"consistent"` -- only units reporting in *every* requested year, giving
+#'     a balanced panel.
+#'
+#'   Regardless of mode, `provenance$coverage` always carries per-year
+#'   `n_units_reporting`, `n_units_expected` and `is_census_year`, and
+#'   `provenance$coverage_mode` records the mode. `is_census_year` is a
+#'   statement about the **survey calendar**, never a claim of completeness:
+#'   FY1967 is a census year in which only 97 of Wisconsin's 608 cities
+#'   report. `n_units_reporting` is the number that tells the truth.
+#'
+#'   The comparison target is exempt from `"consistent"` balancing -- it is the
+#'   subject of the comparison, not a member of the cohort -- and the
+#'   `summary_*` quantiles are computed AFTER the filter, so they describe the
+#'   cohort actually returned. `n_units_reporting` counts peers only, against
+#'   the cohort size: "3 of your 15 peers reported in FY2019".
 #' @return Tibble matching [cog_spending()]'s columns, plus a `role`
 #'   column taking values `"target"`, `"peer"`, `"summary_p25"`,
 #'   `"summary_p50"`, or `"summary_p75"`, `target_rank` (target's rank
@@ -186,9 +242,11 @@ cog_find_peers <- function(target_govid,
 #' @export
 cog_peer_compare <- function(target_govid, peers, category, years,
                              per_capita = TRUE, adjust_to_year = NULL,
-                             expenditure_concept = c("direct", "total")) {
+                             expenditure_concept = c("direct", "total"),
+                             coverage = c("all", "census", "consistent")) {
   call <- match.call()
   expenditure_concept <- match.arg(expenditure_concept)
+  coverage <- .validate_coverage(coverage)
   if (identical(expenditure_concept, "total")) {
     .abort_concept_not_aggregatable("cog_peer_compare")
   }
@@ -211,9 +269,20 @@ cog_peer_compare <- function(target_govid, peers, category, years,
   peer_govids <- peer_govids[!is.na(peer_govids) & nzchar(peer_govids)]
   all_govids <- unique(c(target_govid, peer_govids))
 
+  years <- .apply_census_years(years, coverage, "cog_peer_compare")
+
   r <- cog_spending(all_govids, years, category, per_capita, adjust_to_year)
   r$role <- ifelse(r$canonical_govid == target_govid, "target", "peer")
 
+  # The target is exempt from balancing: it is the subject of the comparison,
+  # not a member of the cohort being balanced, and dropping it would leave a
+  # peer comparison with nothing to compare. Filtering happens BEFORE the
+  # quantiles below, so a "consistent" cohort's summary rows describe that
+  # cohort rather than the unbalanced one.
+  if (identical(coverage, "consistent")) {
+    r <- .filter_consistent(r, years, keep_ids = target_govid)
+  }
+
   value_col <- .peer_value_col(per_capita, adjust_to_year)
 
   summary_rows <- .peer_summary_rows(r, value_col)
@@ -234,6 +303,14 @@ cog_peer_compare <- function(target_govid, peers, category, years,
     canonical_govid = target_govid,
     gov_name        = unique(r$gov_name[r$role == "target"])
   )
+  # Counted over PEER rows only, against the cohort size: "3 of your 15 peers
+  # reported in FY2019". Including the target would inflate every count by one
+  # and make a cohort that has entirely stopped reporting look non-empty.
+  prov$coverage_mode <- coverage
+  prov$coverage <- .coverage_table(
+    out, years, length(peer_govids),
+    rows = r[r$role == "peer", , drop = FALSE]
+  )
   attr(out, "provenance") <- prov
   out
 }

R/rollup.R

@@ -31,6 +31,25 @@
 #'   across multiple layers of government double-counts intergovernmental
 #'   transfers (a state's payment to a school district is the same dollar the
 #'   district reports as its own Direct spending).
+#' @param coverage How to handle the Census of Governments survey cycle,
+#'   which is a **complete census only in years ending in 2 and 7** -- every
+#'   other year is a sample, and the sample varies enormously (on the bundled
+#'   fixture, Wisconsin's 608-city universe reports 597 governments in FY2012
+#'   and 112 in FY2019).
+#'
+#'   * `"all"` (default) -- every unit that reported that year. Unchanged
+#'     behaviour, so existing code keeps working.
+#'   * `"census"` -- census years only. Aborts if the requested range holds
+#'     none, rather than silently returning nothing.
+#'   * `"consistent"` -- only units reporting in *every* requested year, giving
+#'     a balanced panel.
+#'
+#'   Regardless of mode, `provenance$coverage` always carries per-year
+#'   `n_units_reporting`, `n_units_expected` and `is_census_year`, and
+#'   `provenance$coverage_mode` records the mode. `is_census_year` is a
+#'   statement about the **survey calendar**, never a claim of completeness:
+#'   FY1967 is a census year in which only 97 of Wisconsin's 608 cities
+#'   report. `n_units_reporting` is the number that tells the truth.
 #' @return Tibble with columns `year`, `layer`, `canonical_govid`, `gov_name`,
 #'   `spend_subtype`, `category`, `amt_nominal`, optional `amt_real` /
 #'   `amt_per_capita_nominal` / `amt_per_capita_real`, optional `pop_source`,
@@ -40,9 +59,11 @@
 #' @export
 cog_geographic_rollup <- function(govids, category, years,
                                   per_capita = FALSE, adjust_to_year = NULL,
-                                  expenditure_concept = c("direct", "total")) {
+                                  expenditure_concept = c("direct", "total"),
+                                  coverage = c("all", "census", "consistent")) {
   call <- match.call()
   expenditure_concept <- match.arg(expenditure_concept)
+  coverage <- .validate_coverage(coverage)
   if (identical(expenditure_concept, "total")) {
     .abort_concept_not_aggregatable("cog_geographic_rollup")
   }
@@ -59,11 +80,20 @@ cog_geographic_rollup <- function(govids, category, years,
     layer           = rep(layer_names, lengths(govids))
   )
 
+  # coverage = "census" drops non-census years BEFORE the query rather than
+  # after: a sample year's rows are not wanted at all, and fetching them only
+  # to discard them would also let them into the coverage table.
+  years <- .apply_census_years(years, coverage, "cog_geographic_rollup")
+
   r <- cog_spending(all_govids, years, category, per_capita, adjust_to_year)
   r <- dplyr::left_join(r, layer_map, by = "canonical_govid",
                         relationship = "many-to-many")
   r$scope_note <- .rollup_scope_note(r$layer)
 
+  if (identical(coverage, "consistent")) {
+    r <- .filter_consistent(r, years)
+  }
+
   excluded <- character(0)
   if (isTRUE(per_capita) && "pop_source" %in% names(r)) {
     drop <- r$pop_source == "unavailable"
@@ -82,6 +112,11 @@ cog_geographic_rollup <- function(govids, category, years,
     included_govids = included,
     excluded_govids = excluded
   )
+  # n_units_expected is the universe the CALLER named -- the govids passed in
+  # -- not the national universe. That is what makes the ratio meaningful:
+  # "597 of the 608 Wisconsin cities you asked about reported in FY2012".
+  prov$coverage_mode <- coverage
+  prov$coverage <- .coverage_table(r, years, length(unique(all_govids)))
   attr(r, "provenance") <- prov
 
   r

man/cog_find_peers.Rd

@@ -11,7 +11,8 @@ cog_find_peers(
   same_state = FALSE,
   pop_range = c(0.7, 1.3),
   is_ratio = TRUE,
-  max_peers = 10L
+  max_peers = 10L,
+  coverage = c("all", "census", "consistent")
 )
 }
 \arguments{
@@ -34,6 +35,14 @@ target's population at `year` to produce absolute bounds. If `FALSE`,
 `pop_range` is interpreted as absolute population counts.}
 
 \item{max_peers}{Integer cap on the number of peers returned.}
+
+\item{coverage}{Survey-cycle handling; see [cog_peer_compare()]. Here it
+governs the cohort VINTAGE when `year` is `NULL`: `"census"` snaps to the
+most recent census year with an observed population, so a cohort is not
+built from a sample year in which most of the candidate universe is
+absent. `"consistent"` needs a year range, which cohort selection does not
+have, so it selects like `"all"` and is carried on the result as
+`attr(x, "coverage")` for [cog_peer_compare()].}
 }
 \value{
 Tibble with columns `canonical_govid`, `gov_name`, `fips_state`,

man/cog_geographic_rollup.Rd

@@ -10,7 +10,8 @@ cog_geographic_rollup(
   years,
   per_capita = FALSE,
   adjust_to_year = NULL,
-  expenditure_concept = c("direct", "total")
+  expenditure_concept = c("direct", "total"),
+  coverage = c("all", "census", "consistent")
 )
 }
 \arguments{
@@ -35,6 +36,26 @@ single-government queries but cannot be used here because combining Total
 across multiple layers of government double-counts intergovernmental
 transfers (a state's payment to a school district is the same dollar the
 district reports as its own Direct spending).}
+
+\item{coverage}{How to handle the Census of Governments survey cycle,
+  which is a **complete census only in years ending in 2 and 7** -- every
+  other year is a sample, and the sample varies enormously (on the bundled
+  fixture, Wisconsin's 608-city universe reports 597 governments in FY2012
+  and 112 in FY2019).
+
+  * `"all"` (default) -- every unit that reported that year. Unchanged
+    behaviour, so existing code keeps working.
+  * `"census"` -- census years only. Aborts if the requested range holds
+    none, rather than silently returning nothing.
+  * `"consistent"` -- only units reporting in *every* requested year, giving
+    a balanced panel.
+
+  Regardless of mode, `provenance$coverage` always carries per-year
+  `n_units_reporting`, `n_units_expected` and `is_census_year`, and
+  `provenance$coverage_mode` records the mode. `is_census_year` is a
+  statement about the **survey calendar**, never a claim of completeness:
+  FY1967 is a census year in which only 97 of Wisconsin's 608 cities
+  report. `n_units_reporting` is the number that tells the truth.}
 }
 \value{
 Tibble with columns `year`, `layer`, `canonical_govid`, `gov_name`,

man/cog_peer_compare.Rd

@@ -11,7 +11,8 @@ cog_peer_compare(
   years,
   per_capita = TRUE,
   adjust_to_year = NULL,
-  expenditure_concept = c("direct", "total")
+  expenditure_concept = c("direct", "total"),
+  coverage = c("all", "census", "consistent")
 )
 }
 \arguments{
@@ -33,6 +34,32 @@ population.}
 `"direct"` is accepted; the `"total"` option exists in [cog_spending()] for
 single-government queries but cannot be used here because combining Total
 across peer sets counts intergovernmental transfers twice.}
+
+\item{coverage}{How to handle the Census of Governments survey cycle,
+  which is a **complete census only in years ending in 2 and 7** -- every
+  other year is a sample, and the sample varies enormously (on the bundled
+  fixture, Wisconsin's 608-city universe reports 597 governments in FY2012
+  and 112 in FY2019).
+
+  * `"all"` (default) -- every unit that reported that year. Unchanged
+    behaviour, so existing code keeps working.
+  * `"census"` -- census years only. Aborts if the requested range holds
+    none, rather than silently returning nothing.
+  * `"consistent"` -- only units reporting in *every* requested year, giving
+    a balanced panel.
+
+  Regardless of mode, `provenance$coverage` always carries per-year
+  `n_units_reporting`, `n_units_expected` and `is_census_year`, and
+  `provenance$coverage_mode` records the mode. `is_census_year` is a
+  statement about the **survey calendar**, never a claim of completeness:
+  FY1967 is a census year in which only 97 of Wisconsin's 608 cities
+  report. `n_units_reporting` is the number that tells the truth.
+
+  The comparison target is exempt from `"consistent"` balancing -- it is the
+  subject of the comparison, not a member of the cohort -- and the
+  `summary_*` quantiles are computed AFTER the filter, so they describe the
+  cohort actually returned. `n_units_reporting` counts peers only, against
+  the cohort size: "3 of your 15 peers reported in FY2019".}
 }
 \value{
 Tibble matching [cog_spending()]'s columns, plus a `role`

tests/testthat/test-coverage-disclosure.R

@@ -30,7 +30,6 @@ wt_coverage <- function(x) {
 }
 
 test_that("multi-government aggregates disclose reporting coverage on every result", {
-  testthat::skip("Blocked on uscogdata#13 (findings F-020, F-023)")
 
   # -- F-020: geographic rollups -------------------------------------------
   # Wisconsin's city/village universe is 608 governments. On the bundled
@@ -49,10 +48,22 @@ test_that("multi-government aggregates disclose reporting coverage on every resu
   expect_equal(cov$n_units_reporting, c(152L, 597L, 112L, 114L))
   expect_equal(cov$is_census_year, c(FALSE, TRUE, FALSE, FALSE))
 
+  # Cross-check against the raw partitions, scoped to the SAME universe the
+  # rollup was given -- the 608 govids above. Scoping instead on the long
+  # table's own `type`/`fips_state` asks a different question and answers 595:
+  # VERNON VILLAGE and WAUKESHA VILLAGE carry type = 3 there (their as-of-year
+  # identity, when they were townships) while the xwalk lists them as
+  # govs_type = 2 (their present identity, as villages). Schema v6 made the
+  # long table's geography present-harmonized and moved as-of-year to the
+  # *_asof columns, but `type` still reads as-of-year -- see .validate_schema()
+  # in R/manifest.R. n_units_reporting counts against the requested universe,
+  # so 597 is the number that answers "how many of the governments I asked
+  # about reported".
   raw_2012 <- wt_raw_query(paste0(
     "SELECT COUNT(DISTINCT canonical_govid) n FROM read_parquet('", wt_corpus_glob(), "') ",
-    "WHERE type = 2 AND fips_state = 55 AND year = 2012 ",
-    "AND LEFT(item_code, 1) IN ('E','F','G') AND NOT is_aggregate"))
+    "WHERE year = 2012 AND LEFT(item_code, 1) IN ('E','F','G') AND NOT is_aggregate ",
+    "AND canonical_govid IN (",
+    paste0("'", wi$canonical_govid, "'", collapse = ","), ")"))
   expect_equal(cov$n_units_reporting[cov$year == 2012], as.integer(raw_2012$n[[1]]))
 
   # -- F-023: peer cohorts --------------------------------------------------