Path-Aware Evidence Stitching for Budgeted Dual-Index Retrieval: A Controlled Multi-Hop Study

Authors

  • Seojun Davis Tandon School of Engineering, New York University, New York, USA Author
  • Julian Tran Tandon School of Engineering, New York University, New York, USA Author

DOI:

https://doi.org/10.66525/ijictt143

Keywords:

retrieval-augmented generation, dual-index retrieval, lexical route stitching, graph skeleton budget, path coverage, synthetic network evaluation

Abstract

Budgeted graph skeletons reduce expensive indexing but can disconnect relational evidence that remains available in a complementary lexical index. We investigate a query-time stitching mechanism that temporarily joins selected graph edges with the highest-ranked lexical candidates and prioritizes a coherent shortest route within the final evidence budget. A workload-weighted selector combines historical query-path counts with edge betweenness; controlled baselines instantiate kNN eigenvector skeleton selection, weighted term–chunk postings, Personalized PageRank, and reciprocal rank fusion. After exploratory development, we freeze the parameters and execute a disjoint evaluation on three fully synthetic stochastic-block corpora containing 1,849 relation records and 480 queries. At 20% skeleton allocation, 100 lexical candidates and top-eight output, route stitching increases strict reference-path coverage of a betweenness skeleton from 13.96% to 57.50%. Workload weighting obtains 59.17% against an otherwise identical betweenness-stitch baseline, a 1.67-point difference with a paired 95% bootstrap interval of −0.63 to 4.17 points. Both stitched variants support some valid shortest route on approximately 98% of queries, and removing PageRank does not lower strict coverage. The findings isolate useful cross-index retrieval behavior under clean synthetic entity metadata; effects on natural-language QA and generation remain to be established.

Downloads

Download data is not yet available.

References

P. Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” Advances in Neural Information Processing Systems, vol. 33, pp. 9459–9474, 2020. Available: https://proceedings.neurips.cc/paper/2020/hash/6b493230205f780e1bc26945df7481e5-Abstract.html.

F. Zhou, “Moment-constrained side-force allocation for wind-assisted merchant ships: Hydrodynamic performance of retractable anti-leeway fins and flap rudders,” Innovation and Technology Studies, vol. 3, no. 1, pp. 27–41, 2026.

S. Robertson and H. Zaragoza, “The Probabilistic Relevance Framework: BM25 and Beyond,” Foundations and Trends in Information Retrieval, vol. 4, nos. 1–2, pp. 1–174, 2009. doi: 10.1561/1500000019.

Z. Yang et al., “HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering,” Proc. EMNLP, pp. 2369–2380, 2018. doi: 10.18653/v1/D18-1259.

X. Ho, A.-K. D. Nguyen, S. Sugawara, and A. Aizawa, “Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps,” Proc. COLING, pp. 6609–6625, 2020. doi: 10.18653/v1/2020.coling-main.580.

D. Teng, “TRIAD: Deadline- and reliability-aware scheduling for post-earthquake structural assessment workflows,” World Journal of Engineering Research, vol. 3, no. 6, pp. 55–66, 2025.

D. Edge et al., “From Local to Global: A Graph RAG Approach to Query-Focused Summarization,” arXiv:2404.16130, 2024.

Z. Guo, L. Xia, Y. Yu, T. Ao, and C. Huang, “LightRAG: Simple and Fast Retrieval-Augmented Generation,” Findings of EMNLP, pp. 10746–10761, 2025. doi: 10.18653/v1/2025.findings-emnlp.568.

B. Jiménez Gutiérrez, Y. Shu, Y. Gu, M. Yasunaga, and Y. Su, “HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models,” Advances in Neural Information Processing Systems, vol. 37, 2024. doi: 10.52202/079017-1902.

X. He et al., “G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering,” Advances in Neural Information Processing Systems, vol. 37, 2024. doi: 10.52202/079017-4224.

B. Chen et al., “PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths,” Proc. AAAI, vol. 40, no. 36, pp. 30183–30191, 2026. doi: 10.1609/aaai.v40i36.40268.

O. Khattab and M. Zaharia, “ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT,” Proc. ACM SIGIR, pp. 39–48, 2020. doi: 10.1145/3397271.3401075.

N. Thakur, N. Reimers, A. Rücklé, A. Srivastava, and I. Gurevych, “BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models,” NeurIPS Datasets and Benchmarks, vol. 1, 2021. Available: https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/65b9eea6e1cc6bb9f0cd2a47751a186f-Abstract-round2.html.

T. Kwiatkowski et al., “Natural Questions: A Benchmark for Question Answering Research,” Transactions of the Association for Computational Linguistics, vol. 7, pp. 452–466, 2019. doi: 10.1162/tacl_a_00276.

J. Wang, Y. Ge, J. Liu, and B. Jiang, “Early warning of liquidity stress in U.S. banks with seasonally aligned frailty hazards and delayed-feedback conformal alarms,” Journal of Trends in Finance and Economics, vol. 1, no. 1, pp. 85–100, 2024.

G. Salton and C. Buckley, “Term-Weighting Approaches in Automatic Text Retrieval,” Information Processing & Management, vol. 24, no. 5, pp. 513–523, 1988. doi: 10.1016/0306-4573(88)90021-0.

L. Page, S. Brin, R. Motwani, and T. Winograd, “The PageRank Citation Ranking: Bringing Order to the Web,” Stanford InfoLab Technical Report 1999-66, 1999. Available: https://netlib.sandia.gov/tex/bib/pagerank.html.

J. Chen, X. Zhang, and X. Han, “Explainable identification of tax-related financial reporting anomalies in U.S. public companies: Cross-fitted tax-consistency residuals and Owen-value Shapley propagation,” World Journal of Economics and Business Research, vol. 1, no. 1, pp. 33–45, 2023.

U. Brandes, “A Faster Algorithm for Betweenness Centrality,” The Journal of Mathematical Sociology, vol. 25, no. 2, pp. 163–177, 2001. doi: 10.1080/0022250X.2001.9990249.

M. Girvan and M. E. J. Newman, “Community Structure in Social and Biological Networks,” Proc. National Academy of Sciences, vol. 99, no. 12, pp. 7821–7826, 2002. doi: 10.1073/pnas.122653799.

E. W. Dijkstra, “A Note on Two Problems in Connexion with Graphs,” Numerische Mathematik, vol. 1, pp. 269–271, 1959. doi: 10.1007/BF01386390.

P. Veličković et al., “Graph Attention Networks,” Proc. International Conference on Learning Representations (ICLR), 2018. Available: https://arxiv.org/abs/1710.10903.

P. W. Holland, K. B. Laskey, and S. Leinhardt, “Stochastic Blockmodels: First Steps,” Social Networks, vol. 5, no. 2, pp. 109–137, 1983. doi: 10.1016/0378-8733(83)90021-7.

D. Teng, “RSRBench: Reproducibility and performance benchmarking for regional seismic risk workflows,” Academic Journal of Architecture and Civil Engineering, vol. 3, no. 1, pp. 40–52, 2025.

Y. A. Malkov and D. A. Yashunin, “Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 42, no. 4, pp. 824–836, 2020. doi: 10.1109/TPAMI.2018.2889473.

V. A. Traag, L. Waltman, and N. J. van Eck, “From Louvain to Leiden: Guaranteeing Well-Connected Communities,” Scientific Reports, vol. 9, article 5233, 2019. doi: 10.1038/s41598-019-41695-z.

W. Zhao, T. Chen, B. Wang, and Z. Shen, “PIPE-RAG: An Execution-Guided Retrieval and Reuse Framework for Reliable Machine Learning Pipeline Code Generation,” WEP Transactions on Computer Science and Intelligent Systems Research, vol. 13, pp. 286–297, 2026.

T. Mo et al., “Self-Evolving AI Agents With Dual Memory for Automated Software Testing and Bug Localization,” IEEE Access, 2026, doi: 10.1109/ACCESS.2026.3713401.

Downloads

Published

2026-10-20