SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions
Jennifer D'Souza, Sameer Sadruddin, Anisa Rula, Ana Bossler, Andrés Fullana, Enric Bas, Syed Ather, Defne Circi, Anlan Chen, L. Catherine Brinson, Alyssa Columbus, George Demetriou, Dongjun Jeong, Tarun Kumar, Frank Krüger, Sascha Genehr, Kai Budde-Sagert, Anamaria Leonescu, Francesco Lodola, Chiara Florindi, Gagana Balasubramanya Murthy, Samson Oluwapelumi Olagbile, Nazia Riasat, Yan Sha, Kevin Shen, Shaokai Yang
cs.DL, cs.AI, cs.CL, cs.IR
Submitted: 2026-07-30
Comments: 25 pages, 9 figures, Submitted for peer review to Nature Scientific Data
Code: https://github.com/sciknoworg/schema-miner
License: http://creativecommons.org/licenses/by-sa/4.0/
The gist: Scientific processes are often described in heterogeneous article discourse, with details needed for comparison, reproducibility, reuse, and automation dispersed across prose, tables, figures,
Terminology
Abstract
Scientific processes are often described in heterogeneous article discourse, with details needed for comparison, reproducibility, reuse, and automation dispersed across prose, tables, figures, protocols, and supplementary files. We present the first release of SciSchema.org, a multidisciplinary collection of 16 expert-annotated schemas spanning Biology & Biotechnology, Materials & Chemistry, Imaging & Measurement, Physics, and Psychology. Each schema defines reusable fields for describing process instances, including inputs, outputs, materials, instruments or software, parameters, conditions, procedural steps, measurements, and provenance-related information. The schemas were created through a human-in-the-loop schema-mining workflow in which large language models generated candidate structures from process specifications, scientific articles, and expert feedback, followed by domain-expert construction of final master schemas. The dataset contains final schemas in JSON Schema and SHACL formats, intermediate model-generated schemas, expert-feedback records, source-paper metadata, community-development materials, and analysis scripts. Technical validation assessed schema structure, development provenance, expert review, and syntactic conformance. The collection supports structured annotation, metadata enrichment, scientific knowledge graphs, information extraction, semantic publishing, and cross-study comparison.
Sources
- OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts
- Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation
- Large Language Models for JSON Schema Discovery
- Conceptual Schema Inference for Tabular Datasets using Large Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Training Compute-Optimal Large Language Models
- Ministral 3
- Qwen3 Technical Report
Related papers
- Persistence Paradox in Dynamic Science: Evidence from the Deep Learning Revolution
- How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?
- MTRACE: Multilingual Retrieval-Augmented Generation for Temporally Diverse Text Corpora
- Eleven Years of BRACIS: A Meta-Scientific Study of the Brazilian Conference on Intelligent Systems
- Evidence-Based Scientific Question Discovery: A Framework with Historical Backtesting