Audit-only first. Activation after evidence.
Tollscopic DOT# can run in a non-actioning mode, collect labelled examples from local traffic, measure performance by condition, and promote downstream uses only when the data supports them.
Five stages. Run in a circle.
The output of each becomes the input of the next. Activation is the gate, not the start. Real production traffic feeds the labels; replay closes the loop.
Categories, not vanity numbers.
The site does not publish exact thresholds or holdout scores. The discipline is the message: each of these is tracked, named, and tied to a decision about activation.
Is the correct carrier in the shortlist at all?
When the top candidate is chosen, is it right?
For events emitted as verified, how often is the carrier correct?
What fraction of eligible commercial traffic emits verified?
Ambiguous + unreadable + no_panel + catalog_miss together.
How often the same physical pass produces more than one event.
From vehicle pass to identity event available for downstream use.
Per-eligible-track event production rate.
Aggregate accuracy hides a multimodal system.
A system that works in clear daytime and collapses at night should not hide behind one number. Tollscopic DOT# reports performance by condition — not just an overall.
Each one is an instrumented category.
Hard cases are not apology. They are how Tollscopic DOT# knows what to improve and how to decide which permissions to activate next. Aggregate hides them; categories surface them.
The panel is behind the trailer for part of the track. Selection and consensus absorb it — most of the time.
Reduced contrast on the panel. Frame selection and preprocess help. Confidence reports it honestly.
Tractor and trailer can show different identities. Tollscopic DOT# is primarily a tractor-door product; mismatch is reported.
Catalog snapshot may be stale. Event class: catalog_miss — flagged for catalog or process review.
Belongs to existing plate workflow. DOT# reports ambiguous; no double-bill risk.
Track fragmentation. The system either reunites tracks or refuses with unreadable.
Stored evidence. Versioned decisions. No silent drift.
When a model, prompt, scorer, or catalog snapshot changes, historical evidence can be reprocessed to understand how the change would have affected real cases. Regression review gates promotion.
Selected frames, trajectory summaries, and observations preserved by track.
Every event records the model, scorer, prompt, and catalog versions that produced it.
New versions can run against historical evidence in parallel to production.
Changes are activated only after no-regression review against the replay corpus.
Audit-only is a real starting point.
It produces useful evidence about your traffic mix before anyone asks Tollscopic DOT# to take stronger action. Activation is the gate at the end of the loop, not at the start.