Goal: place skills from work samples in a curated taxonomy and score them against observable behaviour anchors, so candidate and role match on evidence.
The research
Skill taxonomies are trees that grow exponentially; flat vector spaces cannot hold them. We embed competencies in hyperbolic and mixed-curvature spaces and bind LLM scoring to observable behaviour.
What it changes in practice
After the rebuild, who fills which role? Matching people and roles on evidence, not on keyword overlap, is part of the Adopt layer.