Adaptive Depth Gating Helps Only in Tight-k Settings on Headline Prerequisite Benchmarks
The paper's Conclusion explicitly narrows the scope of any adaptive-depth-gating benefit: adaptive gating helps primarily in tight- settings and remains statistically tied to the fixed-depth hierarchical baseline at on all three headline datasets (LectureBank-Full, MOOC-CS, QASC). This tight- qualifier is the conclusion-level scope statement for adaptive depth gating: any practical advantage shows up at small retrieval cutoffs rather than at the headline reporting depth.
0
1
Tags
Science
Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls
Related
Primary and Secondary Retrieval Metrics in Hierarchical Prerequisite Graph RAG
Adaptive Depth Gating Helps Only in Tight-k Settings on Headline Prerequisite Benchmarks
LectureBank-Full Tight-Budget Advantage of Adaptive Depth Gating (Mean ΔR@k = +2.13 over k∈{1,2,3,4})
When Adaptive Depth Helps vs When Fixed-Depth Is Safer (Budget/Cap Guidance)
Three Durable Signals of Strict-Parity Prerequisite Retrieval
Adaptive Depth Gating Helps Only in Tight-k Settings on Headline Prerequisite Benchmarks
HotpotQA External-Validity Probe: Adaptive Depth Does Not Transfer to a Denser Non-Prerequisite Graph (FullWiki-1k: Flat 93.4 / Hier 92.9 / Adaptive 94.0 R@10)