organizational card for paper project

README.md

@@ -7,4 +7,23 @@ sdk: static
 pinned: false
 ---
 
-Edit this `README.md` markdown file to author your organization card.
+# Open Multi-Label ASJC Classification
+
+This Team Space hosts the **open, multi-label implementation of the All Science Journal Classification (ASJC) taxonomy**, designed to classify scientific documents at the individual level.
+
+## Purpose
+Traditional ASJC classification is limited by incomplete sources, journal-level labels, and single-label assignments. This project provides:  
+- **Multi-label classification across 307 subjects**  
+- Fine-tuned **SciBERT model** trained on Crossref metadata  
+- Methods for **collection-level analysis** (researcher portfolios, institutions, datasets)
+
+## Features
+- High accuracy: F1-score 0.892 (307 subjects), 0.934 (26 parent subjects)  
+- Works with or without source title metadata  
+- Open, reproducible, and ready for research use
+
+## Contents
+- Models, code, and notebooks for reproducing results  
+- Example datasets and label-averaging utilities
+
+**Team:** Michael Gusenbauer, Jochen Endermann, Harald Huber, Simon Strasser, Andreas-Nizar Granitzer, Thomas Ströhle