How we rank stories
This section is currently available in English only.
Same for everyone
Every visitor to ovr.news sees the same stories in the same order. There is no personalization. No reader profiles. No engagement optimization. No A/B testing on article order.
Most news platforms rank content to maximize engagement: clicks, time on site, scroll depth. That creates filter bubbles — each reader sees a different version of reality shaped by their past behavior.
We rank content to surface what matters, not what performs. The algorithm is deterministic: given the same articles at the same time, every visitor sees the same result. This page publishes the full formula.
The ranking formula
Each lens orders its articles in two steps. Age decides first, then score.
- Five fresh slots. The five highest-scoring articles published in the last 24 hours go to the top of the lens.
- Age bands. Every other article falls into one of three bands: under 3 days old, 3 to 7 days old, and older. A younger band always comes before an older one. Inside a band, the higher score comes first.
The score is the weighted average across all scoring dimensions for that lens (0 to 10). See how we select stories for how scores are computed. Lens pages show articles from the last 10 days. An article with no publication date or no score goes to the bottom.
So a strong article from yesterday sits above a stronger one from last week, and a weak article from today does not push out a strong one from yesterday unless it is among the five fresh slots.
A correction (October 2026). Until 15 October 2026 this page published a different formula: score × 0.85age_days, with a 1.3× boost in the first 24 hours. The site used it until that day. Earlier, the formula also listed a corroboration boost and a diversity boost; from April 2026 neither changed the order you saw, because a later sorting step discarded both. We found that by rebuilding the live Belonging page without them, which matched all 507 positions, and removed both.
Score threshold
An article needs a weighted average of at least 4.5 out of 10 to appear on the site. Below that threshold, the article is filtered out during the build. This is a quality floor, not a ceiling — most articles that make it to the site score considerably higher.
Editorial rules
After ranking, an editorial layer makes final adjustments. Its rules are deterministic checks with configurable thresholds, and every removal is logged with a reason. An AI editorial gate we tried is switched off; the trust page says why.
- Story dedup. When several outlets cover the same story, you see one version. Most duplicates are removed upstream, before scoring; the dedup page explains how.
Homepage interleaving
The homepage draws from all five lenses using round-robin interleaving: one from Thriving, one from Belonging, one from Recovery, and so on. This ensures every lens gets represented, regardless of which lens has the highest-scoring articles that day.
Within each lens, articles appear in the order described above. Between lenses, representation is equal.
What we don't do
- No click tracking
- No personalization
- No engagement metrics
- No A/B testing on article order
- No advertiser influence on ranking
- No premium placement
The scoring filter definitions are published in llm-distillery on GitHub. The ranking formula is documented in full on this page.
Last updated: July 2026