Ghost Visualizer, a visual essay that computes safety scores
Ghost Visualizer is a seven-scene React/Vite visual essay ("Why AI Safety Scores Lie") that computes marginals, OR composition, Fréchet–Hoeffding bounds, endpoint witnesses, and a receipt object from deterministic sample rows, with an Evidence Mode for inspection.
01Falsifier — what changes this claim
A local run from the bound revision lacks the stated seven scenes, deterministic sample-row computations, or Evidence Mode for inspection.
Consequence NARROW
This is the condition and consequence recorded in the registry. The vocabulary this is published in defines what each consequence commits the author to.
02Scope
The repository at the bound commit. Runs locally; there is no hosted deployment, so the site links source, not a live demo.
03Forbidden rescues
Repairs declared unavailable in advance; using one after a failure would breach the recorded commitment.
do not count hard-coded or mocked screenshots as deterministic computations
do not recast a local-only source project as a hosted interactive demo
04Non-claims — what this does not license
not an AI-safety certificate; no deployment-readiness claim
its own public-readiness review scores it for private serious-contact demo use; the site therefore links source rather than exhibiting its media as a flagship
05Binding and freshness
Binding
Cubits11/ghost-visualizer @ 3fbe3efc Re-reviewed 2026-08-23 when the public-readiness non-claim was added; entry edits and review dates travel together.
Reviewed
2026-08-24 · window 120 days
Expires
2026-12-22 — after this date the recorded review is overdue; this does not make the claim false
Triggers
executable fires when the README on the default branch is reframed
manual hosted deployment added — the site may then link a live demo
Dimensions
visibilityPublicprovenanceOwner-authored, publicsupport roleRepository READMEmaturityIn development