Methodology · Source Collection
Updat3 ingests articles from multiple news APIs every 30 minutes, groups related articles into single stories, and removes duplicates automatically.
Articles are pulled every 30 minutes from a combination of news APIs covering hundreds of international outlets. Only English-language articles are processed (or articles that can be translated automatically). Articles must have a title, a URL, and at least a brief excerpt to be stored.
Multiple articles about the same event are merged into a single story. This is how you see "5 sources" under one headline instead of five separate cards.
Matching uses a combination of:
Semantic similarity
Article text is converted to a vector embedding and compared against existing story embeddings. Articles above the similarity threshold are candidates for merging.
Title overlap
Shared significant words between article and story titles provide a secondary signal.
Entity matching
Named people, places, and organisations mentioned in both articles boost the match score.
Fact overlap
Key factual statements from both articles are compared for shared content.
Matching errors happen. An article about one Iran story may occasionally be grouped with a different Iran story. We run merge and re-link passes continuously to correct this.
We filter articles at ingestion and again before AI enrichment. Filtered types include:
Once an article passes quality filters, it is processed by an AI model that writes:
The AI is explicitly instructed to write from no government's default perspective, apply identical framing standards to all parties, and include historical context that implicates powerful actors — not just the most recent provocation.