Learn Before
MOOCCubeX Large-Scale MOOC Concept-Graph Resource (Yu et al., 2021)
Pan et al. (2017) Prerequisite Relation Learning for Concepts in MOOCs
Datasets (Experimental Setup) 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)
MOOC-CS Configuration Used in Hierarchical Prerequisite RAG (225 Concepts, 516 Edges, 1,016 QA)
In this paper, MOOC-CS is consumed as a prerequisite graph with concepts, prerequisite edges, and QA pairs derived from the MOOCCubeX computer-science curriculum, with prerequisite-relation lineage from Pan et al. (2017). Graph descriptors computed from the released graph and concept texts are: mean depth , fraction of nodes with depth equal to , mean degree , and mean concept-text length tokens. Compared to LectureBank-Full, MOOC-CS is deeper but sparser in degree and uses much shorter concept texts.
0
1
Tags
Science
Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls
Related
MOOC-CS Configuration Used in Hierarchical Prerequisite RAG (225 Concepts, 516 Edges, 1,016 QA)
Prerequisite Graphs Consumed as Retrieval Substrates, Not Inferred
MOOC-CS Configuration Used in Hierarchical Prerequisite RAG (225 Concepts, 516 Edges, 1,016 QA)
LectureBank-Full Configuration Used in Hierarchical Prerequisite RAG (208 Concepts, 899 Edges, 1,421 QA)
MOOC-CS Configuration Used in Hierarchical Prerequisite RAG (225 Concepts, 516 Edges, 1,016 QA)
Canonical Prerequisite Splits Are Heavily Templated: 92/80 LectureBank-Full and 68/60 MOOC-CS Train-Test Overlaps
QASC Rebuilt as Directed Science-Fact Graph (16,444 Nodes, 25,590 Edges) Used Only for Validation Retrieval
Induced HotpotQA Slice as Auxiliary Stress Test in Supplement
MOOC-CS Graph Gain Requires Language-Matched Controls
MOOC-CS Configuration Used in Hierarchical Prerequisite RAG (225 Concepts, 516 Edges, 1,016 QA)
MOOC-CS Headline R@10 Numbers: LightRAG/Truncated-PPR 25.6-25.9 vs Adaptive/Hierarchical Tied at 23.1
MOOC-CS Target-Disjoint R@10 Result (n=114): Negative Case, Adaptive Tied
Template Stripping on MOOC-CS Raises Hierarchical R@10 from 23.1 to 26.5 (MiniLM Encoder)