various edits

docs/dashboard_spec.md

@@ -31,6 +31,13 @@ headlined, or described as population county performance.
 ### Sample cohorts
 
 - Search and compare only supported, suppression-cleared make/model cohorts
+- Combine documented source abbreviations and trim labels for newly published
+  model families before applying the unchanged publication thresholds
+- Keep earlier public cohort definitions stable across releases so differences
+  cannot expose a formerly suppressed slice
+- Identify Silverado 1500, Ram 1500, Elantra, Altima, Outback, 4Runner,
+  Corolla, and Tacoma as combined families; identify F150, Accord, Civic, and
+  Camry as exact source-label cohorts
 - Show observed sample non-pass rates and rounded support
 - Default sorting by support rather than risk
 - Disable filters or adjusted views that the aggregate bundle cannot support

docs/demo_script.md

@@ -53,7 +53,9 @@ the “observed sample non-pass” label.
 **Say:**
 
 > This view contains only prior make-and-model cohorts that cleared the
-> publication thresholds. I can search supported cohorts, but these are observed
+> publication thresholds. Selected source abbreviations and trim labels are
+> combined for new model families, while earlier published cohorts keep stable
+> definitions. I can search supported cohorts, but these are observed
 > development-sample associations—not reliability grades, rankings, or
 > recommendations. Unsupported slices are not inferred in the browser, and
 > suppressed rows are absent rather than hidden.

docs/final_report.md

@@ -140,7 +140,9 @@ views:
 
 1. **Overview** shows rounded support, sample outcome patterns, vehicle-age
    patterns, and county feed coverage.
-2. **Sample cohorts** shows only supported make/model sample aggregates; it does
+2. **Sample cohorts** shows only supported make/model sample aggregates;
+   selected source abbreviations and trim labels are combined for new model
+   families while earlier published cohorts keep stable definitions. It does
    not issue reliability ratings or recommendations.
 3. **Model & benchmark** identifies calibrated logistic regression as final and
    the boosted tree as benchmark-only. It shows pre-2025, 2024 calibration-fit

docs/model_card.md

@@ -132,7 +132,8 @@ population or external-validation results.
 - Page sampling is not population-representative.
 - Source, program, time, and geography are entangled.
 - Reject and abort are heterogeneous non-pass outcomes.
-- Make/model aliases and incomplete feed coverage can distort cohorts.
+- Residual make/model aliases outside the documented scorecard mappings and
+  incomplete feed coverage can distort cohorts.
 - The one-time 2025 holdout is not an external validation dataset.
 - No protected attributes are modeled, but that does not establish fairness.
 - Sample calibration does not establish production calibration.