Learn Before
QASC Directed Science Fact Graph Reconstruction (16,444 Nodes, 25,590 Edges)
In this paper, QASC is rebuilt as a directed science fact graph with nodes and edges, giving a much larger and structurally different substrate than the two curated prerequisite DAGs. Because the official QASC test split withholds evidence, the paper reports retrieval results only on the -question validation split. Graph descriptors are: mean depth , fraction of nodes with depth equal to , mean degree , and mean text length tokens.
0
1
Tags
Science
Auditable Strict-Parity Evaluation of Prerequisite-Graph Retrieval for RAG under Leakage Controls
Related
QASC Directed Science Fact Graph Reconstruction (16,444 Nodes, 25,590 Edges)
QASC Strict-Parity Result: ColBERTv2/RePlug Strongest (R@10 = 85.0 [83.4, 86.6])
QASC Generation Diagnostic: TF-IDF Multiple-Choice Scorer 76.8% (Hierarchical) vs 74.6% (Adaptive)
QASC Conclusion: Reranking Beats Hierarchical and Adaptive Graph Traversal
QASC Paired Delta: Adaptive vs Hierarchical Baseline = +0.5 [-0.5, +1.5]