Retina

Retina is the lab’s news perception. It is built embedding-first: every article is turned into a vector before anything else happens, so that similarity, clustering and search all work on meaning rather than keywords. A language model then extracts the entities each article mentions (people, places, organisations, events, assets) at a measured precision of 95.7 %, and links them to a curated catalogue. Storylines are clusters of articles that stay together over days; bursts are names that suddenly outrun their own baseline; tone is a sentiment score per article, aggregated per entity.

Sources are ordinary: RSS from newspapers, broadcasters, agencies and specialist outlets, a set of public Telegram channels, and a few sources that are only reachable over Tor, routed through the lab’s own gateway. Nothing is scraped that a publisher hides behind a login. Retina keeps derived data; the articles stay with their publishers.

Retina replaced a much larger predecessor on 26 March 2026: fifty-seven containers and more than two hundred tools, retired in one move for a single service with one job. The 96 % did not come for free either. Until July 2026 articles were linked to entities by vector similarity, and when that was measured it reached 2.4 % precision on a test name. The language-model extraction had been running alongside all the time, its results thrown away; since 18 July it is the only source of the links. Consent, login and bot pages are recognised before any request is made and dropped: about 5 % of the inflow, an extrapolation from the first afternoon and a check of 78 cases; the seven-day measurement runs until 8 September.

Since 22 September 2026 a small fine-tuned decision model (see The Model Lab) reads every new article and answers four questions: topic, reach, violence and harm to civilians. Articles whose expected reach stays below a set threshold are set aside, not deleted; in the first run that was 42 % of two days’ inflow. Whether the threshold keeps the right articles is checked by hand against what it set aside.

The numbers below are read from the running system on the day of the snapshot. Retina feeds the actor graph, the situation picture and the network on the front page.