MediaMeter Knowledge Base

Detection signals and verdict bands

How synthetic-media detection is specified to work: modalities, the five verdict bands, provenance verification, and why detection advises while humans decide.

Specification reference

This describes the synthetic-media detection specification — the verdict bands, review routing, and provenance checks. Detection is a signal, never proof; design, not deployed capability.

Synthetic-media detection is probabilistic: generators improve faster than detectors, models drift, and a confident output can still be wrong. Our specification treats detection as one input into an editorial decision — never the decision itself.

The four modalities

Signals are collected separately for text, image, audio, and video, plus a cross-modal flag when a package’s components disagree (e.g., authentic audio with synthetic visuals). Different detector families cover different modalities — no single provider covers all four reliably, which is why the specification calls for a provider ensemble rather than a single detector.

The five verdict bands

Each piece of content resolves into one of five bands:

Band Meaning Routing
AUTHENTIC Signals consistent with human/original production No escalation
likely_authentic Mostly consistent; minor anomalies No escalation
uncertain Signals mixed or weak Medium-priority human review
likely_ai Signals lean synthetic High-priority human review
AI_GENERATED Signals strongly synthetic Critical — mandatory human review before any verdict

A suspected deepfake is disqualifying by design: it caps assessment at the lowest rating and always routes to a human — because a deepfake is not a quality defect to grade but an integrity event to escalate.

Provenance verification

Detection signals are statistical; provenance is a document trail. The specification checks:

  • C2PA manifests — cryptographically signed content credentials recording capture device, edits, and software. A valid manifest from a trusted signatory is stronger evidence than any classifier.
  • SynthID — Google’s watermarking for AI-generated media (specified, not yet enabled).
  • EXIF/XMP metadata — camera and editing-tool data; weak alone (trivially stripped) but corroborating.

Detection and provenance answer different questions — “does this look synthetic” vs. “where did this come from” — and the specification treats their disagreement as its own flag.

The editorial rules

  • Detection advises, editors decide — no automated publish/reject is triggered by a detection score.
  • Disclosure, not just penalty — AI involvement that is disclosed (as the EU AI Act requires) is assessed differently from the same content undisclosed.
  • Re-evaluation on drift — detector providers are re-evaluated on a rolling benchmark; a provider that falls below threshold is disabled rather than silently down-weighted.
  • Review SLAs by band — deepfake/AI-GENERATED flags route critical; likely_ai and cross-modal flags route high; uncertain routes routine review.

Last reviewed: October 20, 2026. Part of the MediaMeter knowledge base — editorial reference material, not product documentation.

More from the knowledge base

The ten elements of journalism

Kovach and Rosenstiel's principles for journalism that serves citizens: truth, verification, independence, and the watchdog role — and why they matter more online, not less.

Journalism ethics codes compared

SPJ, NUJ, IFJ, AFP, Reuters, the German Pressekodex and the UK's IPSO code: what the major ethics frameworks require, where they agree, and where they differ.

News values and story strength

How editors decide what is news: Galtung and Ruge's classic factors, David Randall's eight values, and why "say stories" sit at the bottom of the scale.