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

arXiv: https://arxiv.org/abs/2607.21610 · HTML: https://mlsanity.com/paper/2607.21610/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 16 of 16)

- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [Document-Level Event Argument Extraction by Conditional Generation](https://mlsanity.com/paper/2104.05919/) (2021)
- [Multi-Sentence Argument Linking](https://mlsanity.com/paper/1911.03766/) (2019)
- [PHEE: A Dataset for Pharmacovigilance Event Extraction from Text](https://mlsanity.com/paper/2210.12560/) (2022)
- [Exploring Large Language Models for Ontology Alignment](https://mlsanity.com/paper/2309.07172/) (2023)
- [Schema-Driven Information Extraction from Heterogeneous Tables](https://mlsanity.com/paper/2305.14336/) (2023)
- [SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents](https://mlsanity.com/paper/2410.21155/) (2024)
- [End-to-End Ontology Learning with Large Language Models](https://mlsanity.com/paper/2410.23584/) (2024)
- [CrudeOilNews: An Annotated Crude Oil News Corpus for Event Extraction](https://mlsanity.com/paper/2204.03871/) (2022)
- [Ontology-grounded Automatic Knowledge Graph Construction by LLM under Wikidata schema](https://mlsanity.com/paper/2412.20942/) (2024)
- [InstructIE: A Bilingual Instruction-based Information Extraction Dataset](https://mlsanity.com/paper/2305.11527/) (2023)
- [IPRE: a Dataset for Inter-Personal Relationship Extraction](https://mlsanity.com/paper/1907.12801/) (2019)
- [Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction](https://mlsanity.com/paper/2010.16275/) (2020)
- [LLMs4OL 2024 Overview: The 1st Large Language Models for Ontology Learning Challenge](https://mlsanity.com/paper/2409.10146/) (2024)
- [Combining Distant and Direct Supervision for Neural Relation Extraction](https://mlsanity.com/paper/1810.12956/) (2018)
- [Ontology Matching with Large Language Models and Prioritized Depth-First Search](https://mlsanity.com/paper/2501.11441/) (2025)

## Abstract (arXiv)

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.