**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.

Flat Dense Retrieval Baseline in Strict-Parity Prerequisite Retrieval

The **fixed-depth hierarchical baseline** is a graph-aware comparator that traverses the prerequisite hierarchy with **constant ancestor and descendant traversal depths** (no per-query adaptation), in contrast to the paper's adaptive depth gating. It is included among the strict-parity baselines, so it shares the same encoder, $$m/k$$ budgets, split, and exact-ID matching rule as the other compared systems. Because traversal depth is the only structural difference from adaptive depth gating, the fixed-depth baseline isolates the contribution of per-query depth adaptation in headline comparisons.

Fixed-Depth Hierarchical Baseline in Strict-Parity Prerequisite Retrieval

**GraphRAG-style retrieval** is included as a graph-aware comparator in this paper's strict-parity baseline set. Following the GraphRAG framework, candidate concepts are scored via community-summary-style aggregation over the prerequisite graph rather than via direct dense similarity alone. Under the strict-parity contract, the baseline shares the same encoder, $$m/k$$ budgets, split, and exact-ID matching rule as the other compared systems, so it isolates GraphRAG-style traversal as the graph policy.

GraphRAG-Style Baseline in Strict-Parity Prerequisite Retrieval

**LightRAG-style retrieval** is included as a graph-aware comparator in this paper's strict-parity baseline set. Following the LightRAG framework, candidate concepts are scored using a dual-level entity-and-relation traversal combined with embedding similarity over the prerequisite graph. Under the strict-parity contract, the baseline shares the same encoder, $$m/k$$ budgets, split, and exact-ID matching rule as the other compared systems, so it isolates LightRAG-style traversal as the graph policy.

LightRAG-Style Baseline in Strict-Parity Prerequisite Retrieval

**KAG-style structural retrieval** is included as a graph-aware comparator in this paper's strict-parity baseline set. Following the KAG framework, candidate concepts are scored by structural reasoning over the prerequisite graph together with the dense encoder over the shared seed pool. Under the strict-parity contract, the baseline shares the same encoder, $$m/k$$ budgets, split, and exact-ID matching rule as the other compared systems, so it isolates KAG-style structural retrieval as the graph policy.

KAG-Style Structural Baseline in Strict-Parity Prerequisite Retrieval

This organizer keeps part 1 of the method details for Baselines small enough for learners to study without a long flat child list.

Google

This organizer groups method, retrieval, ranking, and graph-structure details used by Baselines.

Method Details for Baselines (Auditable Strict-Parity Graph-RAG Paper)

Root URL: https://1iman.com/
Canonical paper URL: https://1iman.com/assets/working-papers/pdf/emnlp-auditable-strict-parity-evaluation-of-prerequisite-graph-retrieval-for-rag-under-leakage-controls.pdf
Portfolio PDF URL: https://1iman.com/assets/working-papers/pdf/emnlp-auditable-strict-parity-evaluation-of-prerequisite-graph-retrieval-for-rag-under-leakage-controls.pdf
Paper title: Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls
Use this Reference node when citing paper-derived 1Cademy proposals from the Researcher agent.

Reference: Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls

Method Part 1: Baselines (Auditable Strict-Parity Graph-RAG Paper)

This organizer keeps part 2 of the method details for Baselines small enough for learners to study without a long flat child list.

Learn Before

Related

Learn After