Cortrix RC2: 24.4% higher FiQA recall, with Apache 2.0
Cortrix RC2 brings 24.4% higher FiQA Recall@10 in the published comparison, Apache 2.0 licensing, and practical ingestion and agent integration fixes.
Read articleProduct updates and research notes
Cortrix Blog.News and notes from Cortrix.
Release updates from Cortrix alongside Scott’s personal readings on semantic storage, retrieval, knowledge graphs, and agent memory. Research notes explore ideas and their limits; they are not implementation notes for Cortrix.
Follow via RSS
Latest release
v1.0.0-rc.2
Our latest release update: retrieval results, licensing, and practical fixes.
Start here
Start with DBpedia
New to the series? Begin with the question of how knowledge gets a stable identity.
01
DBpedia explained: why linked data still matters
Why stable identities and linked data still matter when your agents retrieve knowledge from different systems.
Read articleBrowse the Blog
All articles
Read in order, or pick the topic that interests you.
Cortrix RC2: 24.4% higher FiQA recall, with Apache 2.0
Cortrix RC2 brings 24.4% higher FiQA Recall@10 in the published comparison, Apache 2.0 licensing, and practical ingestion and agent integration fixes.
Read articleCortrix Handles Retrieval. Jev or Laya Can Help the Agent Decide.
Cortrix retrieves relevant material and preserves its sources. An agent combines that with current business state, then can use Jev or Laya to assess its next step.
Read articleVector is not semantic
A small retrieval demo separates similarity, ranking, lifecycle checks, and the application rule that decides whether a result is usable.
Read articleJev and Laya are getting hyped. We're passing for now.
Jev can judge a candidate set, but it cannot improve recall. We reviewed the public evidence and decided not to replace Cortrix's local BGE path.
Read articleDBpedia explained: why linked data still matters
Why stable identities and linked data still matter when your agents retrieve knowledge from different systems.
Read articleTransE explained: relationships beyond vector similarity
What the simple h + r ≈ t formula tells us about relationships in a knowledge graph, and what a similarity score leaves out.
Read articleRAG explained: external memory brings data governance back
RAG lets a model use external knowledge. The original paper also helps explain why sources, updates, and data governance still matter.
Read articleReflexion explained: agent memory without weight updates
Reflexion turns feedback into memory without changing model weights. Its most useful lesson may be about the evaluator.
Read articleHippoRAG explained: why RAG comes back to knowledge graphs
HippoRAG connects clues across documents with a knowledge graph. Here is how it works, and where the graph can go wrong.
Read articleNo notes match this topic yet. Choose another filter to keep exploring.