Guardado en:
Detalles Bibliográficos
Autores principales: Qi, Jingxuan, Ye, Zhiqiang, Feng, Yuxiang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.21974
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913151963889664
author Qi, Jingxuan
Ye, Zhiqiang
Feng, Yuxiang
author_facet Qi, Jingxuan
Ye, Zhiqiang
Feng, Yuxiang
contents An extraction schema should not reduce knowledge graph fidelity. On statistical CSV, however, it can. We study country-by-year time-series matrices, a common layout on open-data portals. In this setting, serialization format and schema constraints interact super-additively. Their joint effect exceeds the sum of independent effects by up to +1.180 (2x2 factorial, 6 datasets). Bootstrap 95% CIs are strictly positive on 4/6 datasets, with strongest evidence on wide Type-II matrices. More critically, a schema applied to a mismatched format can trigger catastrophic mismatch. Fact coverage falls below the unconstrained baseline on 4/6 datasets through entity inflation or extraction refusal. We call this observed pattern format-constraint coupling. Probing and token ablation support a surface-form anchoring explanation centred on column-name references. Controlled variants across format-schema pairings, GraphRAG hosts, and LLM families show the same direction within the measured scope; one LLM family shows only partial activation. The observation also has a diagnostic consequence. Three standard retrieval modes largely mask construction quality (delta <= 1pp), whereas direct graph access exposes gaps up to +47.6pp (p < 0.0001). To support fidelity-aware evaluation, we release CSVFidelity-Bench. It contains 15 datasets, 11 Type-II matrices, 4 Type-III tables, and 1,892 Gold Standard facts across 6 domains.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21974
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables
Qi, Jingxuan
Ye, Zhiqiang
Feng, Yuxiang
Artificial Intelligence
An extraction schema should not reduce knowledge graph fidelity. On statistical CSV, however, it can. We study country-by-year time-series matrices, a common layout on open-data portals. In this setting, serialization format and schema constraints interact super-additively. Their joint effect exceeds the sum of independent effects by up to +1.180 (2x2 factorial, 6 datasets). Bootstrap 95% CIs are strictly positive on 4/6 datasets, with strongest evidence on wide Type-II matrices. More critically, a schema applied to a mismatched format can trigger catastrophic mismatch. Fact coverage falls below the unconstrained baseline on 4/6 datasets through entity inflation or extraction refusal. We call this observed pattern format-constraint coupling. Probing and token ablation support a surface-form anchoring explanation centred on column-name references. Controlled variants across format-schema pairings, GraphRAG hosts, and LLM families show the same direction within the measured scope; one LLM family shows only partial activation. The observation also has a diagnostic consequence. Three standard retrieval modes largely mask construction quality (delta <= 1pp), whereas direct graph access exposes gaps up to +47.6pp (p < 0.0001). To support fidelity-aware evaluation, we release CSVFidelity-Bench. It contains 15 datasets, 11 Type-II matrices, 4 Type-III tables, and 1,892 Gold Standard facts across 6 domains.
title Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables
topic Artificial Intelligence
url https://arxiv.org/abs/2605.21974