Matched-Budget Best-First Traversal Comparator in Strict-Parity Prerequisite Retrieval
The matched-budget best-first traversal comparator is a graph-aware strict-parity baseline in which the prerequisite graph is traversed by expanding the highest-scoring frontier node first, subject to the same node/edge/token budget as the paper's diffusion retriever. Under the strict-parity contract, it shares the same encoder, budgets, split, and exact-ID matching rule as every other compared system, so any difference between this comparator and the paper's diffusion policy is attributable to the graph policy itself (best-first traversal versus dense-seeded local diffusion with role-aware quotas) rather than to budget or interface differences.
0
1
Tags
Science
Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls
Related
Matched-Budget Best-First Traversal Comparator in Strict-Parity Prerequisite Retrieval
Budgeted Best-First Traversal Baseline Motivated by Anytime Search (Auditable Strict-Parity Graph-RAG Paper)
Matched-Budget Best-First Traversal Comparator in Strict-Parity Prerequisite Retrieval
Budgeted Best-First Traversal Baseline Motivated by Anytime Search (Auditable Strict-Parity Graph-RAG Paper)
Token-Cap Diagnostic Under a Shared Serialization Policy
Matched-Budget Best-First Traversal Comparator in Strict-Parity Prerequisite Retrieval
LectureBank-Full Paired Delta: Adaptive vs Hierarchical Baseline = +0.7 [-2.1, +3.6]
Multilingual Encoder + CJK Query Rewrite as a MOOC-CS Control
ColBERTv2/RePlug Reranking Baseline for Strict-Parity Prerequisite Retrieval
Truncated Personalized PageRank Baseline for Prerequisite Retrieval
Matched-Budget Best-First Traversal Comparator in Strict-Parity Prerequisite Retrieval
Multilingual Encoder + CJK Query Rewrite as a MOOC-CS Control