AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

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

Miaobo Hu, Xiaobo Guo, Shuhao Hu, BoKun Wang, Rui Chen, Xin Wang, Jun Xiao, Daren Zha

ICML 2026 · Graph learning › Knowledge and temporal graphs · approach: Graph-based dialog systems · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add candidate-space constraints and contract-based abstraction (SCION-lite vs ETA)extract-then-aggregate baseline · SCOPE core suiteLiteral F1: +0.0455 Literal F1 (0.7063 -> 0.7518)Improved
add candidate-space constraints and contract-based abstraction (SCION-lite vs ETA)extract-then-aggregate baseline · SCOPE core suiteGraph F1: 0.7629 -> 0.7888Improved
constrained pipeline instead of free LLM-only induction (SCION-lite vs LLM-only GPT-5.2)GPT-5.2 Chat · SCOPE core suiteContinuous F1: 0.8549 -> 0.8909Improved
replace proprietary schema engineer with RL-trained Qwen3-8B (SCION-RL)SCION-lite · SCOPE core suiteGraph F1: 0.7888 -> 0.8228Improved
add deterministic typed-edge completion to released source schemas (ablation)released source schemas · SCOPE core suiteContinuous F1: +0.0179 Continuous F1Improved
evaluate against train-derived reachable target instead of full gold (ablation)SCION-lite · SCOPE core suiteLiteral recall: 0.7145 -> 0.8464Improved
use SCION-lite schema instead of ETA or released schema in a fixed extractordownstream extractor · Downstream instance-level extractionmacro F1: 0.5633 -> 0.6800Improved
add schema fusion to SCION-liteSCION-lite · Downstream instance-level extractionmacro F1: 0.6800 -> 0.6900Improved
swap GPT-5.2 Chat for DeepSeek-R1 in LLM-only inductionLLM-only baseline · SCOPE core suiteLiteral F1: 0.6836 -> 0.5664Hurt
add structural checks to fusion matching (ablation)fusion matcher · Fusion audit (5k pair budget)mapping precision: 0.81 precision, 0.06 conflict rateImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy