Bayesian predict-calibrate extraction with split-sample validation and EQS scoring

Knowledge graph extraction pipeline produced noisy entities — verbose Domain definitions, hallucinated concepts, entities that didn't improve search retrieval quality. No empirical validation: every extracted entity was accepted into the graph regardless of whether it helped agents find relevant content. Scattered quality signals (pageRank, effectivenessScore, trustTier) with no unified scoring.

Additionally, the prediction system used bayesian-primary-with-LLM-fallback gating, which underperformed on sparse graph areas (~60% of pairs) where the bayesian system had insufficient structural evidence.