When Does Graph Expansion Help Personal-Corpus Retrieval? A Query-Class-Stratified Evaluation Protocol for Retrieval over Human-Curated Wikilink Graphs, with Pilot Telemetry from a Production Deployment

Anton Dziatkovskii · ORCID 0000-0001-7408-3054

Preprint, 7 September 2026. Version of record: Zenodo, DOI 10.5281/zenodo.22639718. License CC BY 4.0.

Full text (PDF, 7 pages, 200 KB)DOICode: sqlite-graph-memory

Abstract

Graph-augmented retrieval (Graph RAG) systems conventionally construct their graph by LLM-based entity and relation extraction. We study an alternative setting, common in personal knowledge management yet under-evaluated: the graph already exists as human-curated wikilinks accumulated in a linked note corpus. We describe a deployed retrieval system over such a corpus (dense retrieval with multilingual-e5, a bounded 1-hop wikilink expansion used strictly for candidate generation, and cross-encoder reranking; SQLite persistence; no graph database and no extraction pass), and report pilot A/B telemetry from production use: on 10 logged production queries compared vector-only versus vector-plus-graph, the graph hop changed the reranked top-12 in 5 cases (promoting 1-3 notes each, all arriving via the wikilink walk) and changed nothing in the other 5. The pilot also surfaced a directional failure mode: expansion appears to help thematic queries and hurt named-entity queries, whose hub-like cards flood the candidate pool. These observations motivate the paper's main contribution: a query-class-stratified evaluation protocol (entity, theme, bridge, compare, temporal strata) for measuring when graph expansion helps, together with ablations (hop depth, neighbour cap, entity gate) and a paired statistical analysis plan. The pilot sample is small (N=10 queries, one corpus, one user) and we state this plainly; the protocol, not the pilot, is the contribution. Code for the retrieval layer is public; the protocol is designed so that any owner of a linked corpus can replicate it on private data without disclosing that data.

Keywords

retrieval-augmented generation · graph RAG · information retrieval · personal knowledge management · wikilinks · evaluation protocol

How to cite

Dziatkovskii, A. (2026). When Does Graph Expansion Help Personal-Corpus Retrieval? A Query-Class-Stratified Evaluation Protocol for Retrieval over Human-Curated Wikilink Graphs, with Pilot Telemetry from a Production Deployment. Preprint. Zenodo. https://doi.org/10.5281/zenodo.22639718

@misc{dziatkovskii2026graphragbenc,
  author    = {Dziatkovskii, Anton},
  title     = {When Does Graph Expansion Help Personal-Corpus Retrieval? A Query-Class-Stratified Evaluation Protocol for Retrieval over Human-Curated Wikilink Graphs, with Pilot Telemetry from a Production Deployment},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.22639718},
  url       = {https://doi.org/10.5281/zenodo.22639718},
  note      = {Preprint, CC BY 4.0}
}

One text, one DOI: the PDF on this page is the Zenodo file byte for byte. Please cite the DOI.