Embedding Research

DCRP Results

Domain-Conditional Retrieval Precision across 2M+ vectors at 8 dimensionality levels.

The Metric

Domain-Conditional Retrieval Precision (DCRP@k) measures retrieval quality within a semantic domain, not across domains. Standard Recall@10 asks "did you find legal documents for a legal query?" DCRP@10 asks "did you find the right legal documents?"

Corpus

Two production vector collections:

Status: Experiments running. Results will be populated here once run_dcrp.py completes against both collections. The experiment tests PCA reduction at 16, 32, 64, 128, 256, 384, 512, and 768 dimensions.

Expected Results

Based on the theoretical framework (PCA variance ≠ semantic information):

← Back to The Dimensionality Illusion