Observed arrival · 2026-09-23
Retrieval Explorables
Interactive lessons on how search scores, retrieves, ranks, and evaluates results.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Search engineers and curious information-retrieval learners
- Worth noticing
- A guided route connects five ranker topics, from BM25 and rank fusion to result diversity.
Field notes
The collection is organized into guided routes, including one that moves from BM25 through behavioural tests and model editing, and another that links vector-search geometry to filtering and hubness. Individual lessons pair interactive demonstrations with named papers, including work on reciprocal rank fusion and approximate nearest-neighbour search. The page also says the project was inspired by Distill and Complexity Explorables.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue