Inspection outcomes over time
A clearer view of the next inspection
Explore aggregate first-attempt outcomes for returning vehicles in participating Utah county feeds. Non-pass combines fail, reject, and abort.
Data through
Unavailable
Waiting for manifest
Dashboard data is unavailable
The approved aggregate files could not be validated. No estimates are being shown.
Quarterly outcomes
First-attempt non-pass trend
Non-pass (fail + reject + abort)
Partial periods and source changes are called out when present.
Feed availability
County coverage
Teal counties appear in the approved inspection feeds. Gray counties are unavailable, not zero.
Age pattern
Non-pass risk by vehicle age
The development bundle does not include confidence intervals; published aggregate rates are shown as points.
Supported aggregate cohorts
Reliability explorer
Compare published observed next-episode non-pass rates. Every result is a supported aggregate cohort—not an individual prediction.
Explorer unavailable
Approved scorecards could not be validated.
Published aggregate comparison
Supported cohort scorecard
No supported cohorts match
Try clearing one or more filters. Suppressed cohorts are never included in the browser bundle.
Cohort estimate · not an individual diagnosis
Next-test risk estimator
This planned tool will combine approved, coarsened attributes to return a calibrated next-episode non-pass probability.
Intentionally disabled
An approved prediction lookup is not available
The estimator will remain off until a privacy-reviewed, suppressed prediction_lookup is published. The current model diagnostics are not enough to serve individual or row-level estimates.
No VIN, plate, exact address, station, free text, or current-test diagnostic will ever be requested.
Future approved output
Designed for calibrated context
- Calibrated non-pass probability and uncertainty
- Relevant aggregate baseline
- High-level factor contributions
- Support and coverage limitations
Transparent by design
Data & methods
How episodes, labels, temporal evaluation, coverage limits, and privacy controls shape every published result.
Live diagnostics unavailable
Static methodology remains below; no performance values are being shown.
Prediction unit
The first attempt of the next inspection episode. Attempts no more than 30 days apart form one episode.
Binary target
Pass versus non-pass. Non-pass combines fail, reject, and abort; blanks and unrecognized outcomes are not labels.
Point-in-time features
Every history window ends before the target episode. Current-test results, diagnostics, stations, and later attempts are excluded.
Availability by source era
Coverage timeline
The slc and slco labels are source eras for Salt Lake County, not separate physical counties.
No random row split
Chronological evaluation
Historical events establish prior context. The 2025 development-sample holdout was evaluated once after model choices were frozen, so it is no longer a pristine final test. A later complete-data run is confirmatory; the partial 2026 feed is monitoring only.
- 2010–15ContextHistory only
- 2016–22TrainFit preprocessing + model
- 2023TuneSelect regularization
- 2024CalibrateScale probabilities
- 2025One-time holdoutAlready evaluated
- 2026ShadowPartial-period drift
Model diagnostics
Published model diagnostics
PR-AUC—
Brier score—
Support—
Interpret with care
Known limitations
- Participating inspection feeds do not cover all 29 counties.
- Feed and program changes can resemble real-world trends.
- DMV history has a 2021 gap and ends in March 2024.
- Reject and abort can reflect process or readiness issues.
- Association is not causation or a mechanical diagnosis.
Publication boundary
Only approved aggregates reach this site
Private source
Read-only local pipeline Suppression
Minimum support + complements Public assets
Aggregate JSON only
Read-only local pipeline Suppression
Minimum support + complements Public assets
Aggregate JSON only
Direct identifiers, private vehicle tokens, plates, ZIPs, stations, raw records, and row-level predictions are outside the public data contract.