How Mosaic works

Mosaic Score (1–10): a weighted composite of how credible the source is, how significant the event is, the model's confidence, and how well the core the model rates the claim. It is a priority for ranking, not an evidence status or a measure of truth. It always sits one hover from the reasoning and one click from the sources.

Source credibility is earned, not assigned. Sources start at an editorial tier, then (once they have enough history) are continuously re-blended by their corroboration rate: how often their claims are later reported by other outlets. Reliable sources rise; sources that publish unconfirmed claims sink. Capped at 0.98. Nothing is ever beyond question.

Evidence status is computed from the evidence, never from the model's own label or from outlet counts. Reported: at least one admissible published item supports it. Corroborated: at least two separate source groups support it, with syndicated, duplicate and shared-origin copies counted once. Confirmed: corroborated, plus a primary, official or documentary source. Verified is reserved for deterministic checks and is never assigned because news sources agree. Missing, conflicting, stale or failed evidence reads Unknown. A Situation never shows a status stronger than its weakest key fact, and confidence is capped by the evidence status.

Anomaly severity (0–10) is driven by the size of the deviation from a subject's own 30-day baseline, log-scaled and volume-damped. A 10× spike on 6 mentions is interesting; a 10× spike on 60 is an event. Fusion alerts (aligned physical + narrative indicators) take the highest component severity plus a bonus, because they are the strongest class of early warning.

Design principle: scores compress evidence. They never replace it.