1Cademy - MOOC-CS Target-Disjoint R@10 Result (n=114): Negative Case, Adaptive Tied

Learn Before

Method Part 2: Question-Disjoint and Target-Concept-Disjoint (Auditable Strict-Parity Graph-RAG Paper)
Leakage Controls (Results) in Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls
Method Part 1: MOOC-CS Prerequisite Benchmark (Auditable Strict-Parity Graph-RAG Paper)

Example

MOOC-CS Target-Disjoint R@10 Result (n=114): Negative Case, Adaptive Tied

Under the target-concept-disjoint control on MOOC-CS ( $n = 114$ ), R@ $10$ is $13.2\%$ $[9.4, 17.3]$ for flat dense, $19.4\%$ $[14.2, 25.3]$ for the fixed-depth hierarchical baseline, and $18.3\%$ $[12.7, 24.1]$ for Adaptive (heuristic). The paired-bootstrap Adaptive $-$ Hierarchical delta at $k=10$ is $-1.2$ $[-2.9, +0.4]$ . MOOC-CS remains a negative case under this stricter split, with Adaptive statistically tied to the fixed-depth hierarchical baseline.

0

1

Updated 2026-05-17

Contributors are:

Who are from:

References

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

Learn Before

Related