Learn Before
LectureBank-Full Prerequisite QA Benchmark
Tight Budgets And Token Caps (Results) in Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls
Method-Related Scope Notes for Adaptive Depth Gating for Prerequisite Retrieval (Auditable Strict-Parity Graph-RAG Paper)
Method Part 2: Adaptive Depth Gating for Prerequisite Retrieval (Auditable Strict-Parity Graph-RAG Paper)
LectureBank-Full Tight-Budget Advantage of Adaptive Depth Gating (Mean ΔR@k = +2.13 over k∈{1,2,3,4})
On LectureBank-Full, paired-bootstrap deltas between Adaptive (heuristic) depth gating and the fixed-depth hierarchical baseline show that adaptive is most plausible in the tight-budget region. Averaged over , the mean points, with a 95% paired-bootstrap CI of . Because the CI includes zero, the aggregate effect is not statistically distinguishable from zero; the tight-budget benefit is best read as a pointwise estimate rather than a regime-wide claim. The effect is also weaker than the diffusion-and-quota gain reported elsewhere in the paper.
0
1
Tags
Science
Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls
Related
LectureBank-Full R@10 Gain from Diffusion and Role-Aware Quotas
LectureBank-Full Configuration Used in Hierarchical Prerequisite RAG (208 Concepts, 899 Edges, 1,421 QA)
LectureBank-Full Target-Disjoint R@10 Result (n=164): Diffusion Gain Survives, Adaptive Tied
LectureBank-Full Generation Diagnostic: Token-F1 1.9 → 18.3, EM Stays 0.0
LectureBank-Full Error Taxonomy: Residual Misses Are Near-Misses Along the Local Prerequisite Graph
LectureBank-Full Paired Delta: Adaptive vs Hierarchical Baseline = +0.7 [-2.1, +3.6]
Token-Cap Comparison on LectureBank-Full: Adaptive Loses More as Cap Tightens
LectureBank-Full Tight-Budget Advantage of Adaptive Depth Gating (Mean ΔR@k = +2.13 over k∈{1,2,3,4})
LectureBank-Full ΔR@k Peaks at k=4 (+6.4 Points, CI [1.0, 11.7])
LectureBank-Full Diffusion Gain over Static Parent Expansion (~18 R@10 Points)
Bounded Held-Out Targets After Strictest Leakage Control (21 LectureBank-Full, 18 MOOC-CS)
LectureBank-Full Decomposition: Diffusion+Quotas Drive ~18 R@10 Points; Contrast Gating Adds At Most ~1 Point (Statistically Tied)
Token-Cap Comparison on LectureBank-Full: Adaptive Loses More as Cap Tightens
LectureBank-Full Tight-Budget Advantage of Adaptive Depth Gating (Mean ΔR@k = +2.13 over k∈{1,2,3,4})
LectureBank-Full ΔR@k Peaks at k=4 (+6.4 Points, CI [1.0, 11.7])
When Adaptive Depth Helps vs When Fixed-Depth Is Safer (Budget/Cap Guidance)
MOOC-CS ΔR@k Curve Stays Near Zero Across k (Adaptive vs Hierarchical)
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)
LectureBank-Full ΔR@k Peaks at k=4 (+6.4 Points, CI [1.0, 11.7])
Bidirectional Diffusion Hyperparameter Settings (LectureBank-Full Main Runs)
MOOC-CS ΔR@k Curve Stays Near Zero Across k (Adaptive vs Hierarchical)
Token-Cap Comparison on LectureBank-Full: Adaptive Loses More as Cap Tightens
MOOC-CS Headline R@10 Numbers: LightRAG/Truncated-PPR 25.6-25.9 vs Adaptive/Hierarchical Tied at 23.1
LectureBank-Full Tight-Budget Advantage of Adaptive Depth Gating (Mean ΔR@k = +2.13 over k∈{1,2,3,4})