1Cademy - Flat Dense Retrieval Baseline in Strict-Parity Prerequisite Retrieval

Learn Before

Dense Seed Pool with L2-Normalized all-MiniLM-L6-v2 Embeddings and Inner-Product Search
Method Part 2: Strict-Parity Evaluation Contract for Graph-Aware (Auditable Strict-Parity Graph-RAG Paper)
Method Part 1: Baselines (Auditable Strict-Parity Graph-RAG Paper)

Concept

Flat Dense Retrieval Baseline in Strict-Parity Prerequisite Retrieval

Flat dense retrieval is the non-graph reference baseline in this paper's strict-parity baseline set. It scores every candidate concept by dense-encoder similarity to the query and returns the top- $k$ without any graph traversal, reranking, or diffusion. Under the strict-parity contract, it shares the same encoder, $m/k$ budgets, split, and exact-ID matching rule as all other compared systems, so it isolates the contribution of "no graph structure at all" and serves as the floor against which every graph-aware retriever is measured.