SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text

• URL: http://arxiv.org/abs/2607.21610v1
• Date: Wed, 20 May 2026 04:43:02 GMT
• Title: SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
• Abstract summary: SCOPE ( Construction and Ontology-induction Pipeline Evaluation) is a train-text-only benchmark for corpus-to-schema induction and optional schema fusion from raw text.<n>SCION ( Construction and Ontology-induction Pipeline Evaluation) is an auditable reference pipeline rather than a new extraction architecture.
• Score: 23.835119696596095
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assume the schema is already available. We introduce SCOPE (Schema Construction and Ontology-induction Pipeline Evaluation), a train-text-only benchmark for corpus-to-schema induction and optional schema fusion from raw text, built from 24 public information extraction sources (15 RE and 9 EE) normalized into evaluation-only gold schema graphs; its core event-extraction target covers event types and within-event argument roles, with inter-event links reported separately. We present SCION (Schema Construction and Induction with Ontology Normalization), an auditable reference pipeline rather than a new extraction architecture; it constructs candidate spaces from train text and restricts naming, merging, filtering, validation, and conservative fusion to candidate-linked evidence under strict JSON contracts. On the SCOPE core suite, SCION-lite attains the highest F1 among released source-schema references, Text2Onto-style, LLM-only, and matched extract-then-aggregate baselines under Literal, Fuzzy, Continuous, and Graph schema-graph metrics, while the compact open-model SCION-RL variant reduces reliance on proprietary LLM schema engineers. These results are reported against normalized typed-edge targets rather than as claims that induced schemas surpass human ontology design; the release includes evidence-linked outputs, parse/fallback logs, candidate retention/merging logs, run manifests, code, and benchmark packages at https://github.com/wandugu/paper_scion.

Related papers

• Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval [19.3757623473603]
  Real-world data spans tables, documents, and semi-structured files with implicit semantics.<n>We present a system that automatically discovers an executable schema from raw multi-source data.
  arXiv  Detail & Related papers  (2026-06-03T20:28:36Z)
• EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement [10.675982676332941]
  Existing approaches treat schemas as fixed and address errors downstream.<n>We frame schema refinement as a constrained optimization problem.<n>We analyze the computational hardness of this problem, which motivates a column-wise greedy decomposition.
  arXiv  Detail & Related papers  (2026-05-01T13:01:59Z)
• DBAutoDoc: Automated Discovery and Documentation of Undocumented Database Schemas via Statistical Analysis and Iterative LLM Refinement [0.0]
  A tremendous number of critical database systems lack adequate documentation.<n>We present DBAutoDoc, a system that automates the discovery and documentation of undocumented relational database schemas.
  arXiv  Detail & Related papers  (2026-03-24T10:42:10Z)
• Schema Matching on Graph: Iterative Graph Exploration for Efficient and Explainable Data Integration [0.0]
  Large Language Models (LLMs) have shown promise in schema matching, but suffer from hallucination and lack of up-to-date domain knowledge.<n>This paper introduces SMoG ( Matching on Graph), a novel framework that leverages iterative execution of simple 1-hop SPARQL queries.<n> Experimental results on real-world medical datasets demonstrate that SMoG achieves performance comparable to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-11-25T13:13:56Z)
• SchemaCoder: Automatic Log Schema Extraction Coder with Residual Q-Tree Boosting [14.204656295848357]
  We introduce a fully automated schema extraction framework, Coder, for a wide range of log file formats.<n>At its core, Coder features a novel Residual-Tree (Q-Tree) Boosting mechanism that iteratively refines schema extraction.<n>Our method partitions logs into semantic chunks via context-bounded segmentation, selects representative patterns using embedding-based sampling, and generates schema code through hierarchical Q-Tree-driven queries.
  arXiv  Detail & Related papers  (2025-08-25T23:12:45Z)
• Schema Lineage Extraction at Scale: Multilingual Pipelines, Composite Evaluation, and Language-Model Benchmarks [3.3705400036304205]
  "Semantic drift" compromises data and governance, and impairs the utility of services like text-to-RAG.<n>This paper proposes a novel framework for the automated extraction of fine-grained schema lineage from multilingual enterprise pipeline scripts.<n>Result: A 32B open-source model, using a single reasoning trace, can achieve performance comparable to the GPT series under standard prompting.
  arXiv  Detail & Related papers  (2025-08-10T05:04:32Z)
• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [80.88654868264645]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification [81.17473088621209]
  We treat event schemas as a form of commonsense knowledge that can be derived from large language models (LLMs) We design an incremental prompting and verification method to break down the construction of a complex event graph into three stages. Compared to directly using LLMs to generate a linearized graph, our method can generate large and complex schemas with 7.2% F1 improvement in temporal relations and 31.0% F1 improvement in hierarchical relations.
  arXiv  Detail & Related papers  (2023-07-05T01:00:44Z)
• Single-Stage Visual Relationship Learning using Conditional Queries [60.90880759475021]
  TraCQ is a new formulation for scene graph generation that avoids the multi-task learning problem and the entity pair distribution. We employ a DETR-based encoder-decoder conditional queries to significantly reduce the entity label space as well. Experimental results show that TraCQ not only outperforms existing single-stage scene graph generation methods, it also beats many state-of-the-art two-stage methods on the Visual Genome dataset.
  arXiv  Detail & Related papers  (2023-06-09T06:02:01Z)
• Schema-adaptable Knowledge Graph Construction [47.772335354080795]
  Conventional Knowledge Graph Construction (KGC) approaches typically follow the static information extraction paradigm with a closed set of pre-defined schema. We propose a new task called schema-adaptable KGC, which aims to continually extract entity, relation, and event based on a dynamically changing schema graph without re-training.
  arXiv  Detail & Related papers  (2023-05-15T15:06:20Z)
• Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing [66.55478402233399]
  We propose a framework to elicit relational structures via a probing procedure based on Poincar'e distance metric. Compared with commonly-used rule-based methods for schema linking, we found that probing relations can robustly capture semantic correspondences. Our framework sets new state-of-the-art performance on three benchmarks.
  arXiv  Detail & Related papers  (2022-06-28T14:05:25Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.