Trust
Evidence-first methodology
Cited Current is designed to summarize events from traceable evidence, not to rephrase individual articles.
From reports to one event
- Discover reports from open data, RSS, and official feeds.
- Normalize URLs, timestamps, language, and source identity.
- Remove exact and near duplicates, then cluster reports describing the same event.
- Extract claims with their source identifiers.
- Compare corroborating and contradictory claims.
- Generate a story only from retained evidence, then verify every sentence.
Confidence
Confidence reflects corroboration, source independence, primary evidence, contradiction severity, and timeliness. It is not certainty.
AI use
Models assist with extraction, comparison, drafting, verification, and social adaptation. Model agreement is never treated as source corroboration.