Zeichnungen Dataset - AI-Enhanced Art Historical Descriptions Zeichnungen Dataset - AI-Enhanced Art Historical Descriptions with Iconography Dataset Overview Processing Pipeline AI Prompts Used KISSKI Cluster Resources Output Structure KISSKI Documentation ICONCLASS Resources Data Usage & Citation Quality Notes Zeichnungen Dataset - AI-Enhanced Art Historical Descriptions with Iconography This dataset contains 224x224 images and relative metadata extracted from the MIDAS XML of the Catalogue of the Photographic Collection of the Bibliotheca Hertziana enriched with AI-generated prose texts and iconographic analysis. The dataset is limited to photographs of objects classified as drawing (Zeichnungen), and has been processed using Google Gemma 2 9B Instruct large language model on the KISSKI HPC cluster of the GWDG. Scripts to process the data on KISSKI have been elaborated with Claude Code in Virtual Studio Code. Dataset Overview Source Data: Original dataset: zeichnungen.tsv (30,000 rows / 29,999 data rows) Extracted from: MIDAS XML format (combined.xml) Source institution: Bibliotheca Hertziana - Max Planck Institute for Art History Image repository: Fotothek der Bibliotheca Hertziana Output: Enriched metadata: TSV files with AI-generated German and English descriptions Iconographic analysis: Descriptions based on ICONCLASS classification 224x224 images downloaded from IIIF Image Api of the Photographic Collection Processing Pipeline 1. Data Extraction Source data was extracted with zeichnungen.xql from MIDAS XML format combined.xml containing structured art historical metadata including: Object titles and descriptions (textobj, textfoto) Artist information (aob30) Location data (aob26, aob28) ICONCLASS codes (a5500) - Standardized iconographic classification Dating and provenance Image references (a8540) The set was limited to 30000 entries. 2. ICONCLASS Cache Preparation ICONCLASS System: Source: ICONCLASS.org - Multilingual classification system for cultural content GitHub repository: https://github.com/iconclass/data Images Download 224x224 images downloaded in advance from the IIIF Service based on gemalde.tsv. The script processing for AI Text Enrichment from the metadata checks that the image has been downloaded, so the output data has a 100% certainty of having a matching image. 28.165 images downloaded from 29,999 rows. This is due to known missing digital images. The dataset corresponds to published data and each row contains the licence and accessibility of the single image, date of creation and last update of the catalogue object. 3. AI Text Generation Model Used: Name: Google Gemma 2 9B Instruct Parameters: 9 billion Quantization: FP16 (no quantization) Context window: 8,192 tokens License: Gemma Terms of Use Processing Workflow: Input cleaning: Removal of numeric codes, normalization of Unicode characters, increased CSV field size limit (10 MB) Paragraph generation: German text from structured metadata ICONCLASS lookup: Offline cache-based iconographic description retrieval Iconographic synthesis: AI-generated description from ICONCLASS codes Translation: German → English Categories processed: paragraph foto DE/EN - Photograph description paragraph obj DE/EN - Object/artwork description paragraph verwalter DE/EN - Collection/custodian information paragraph standort DE/EN - Location information paragraph iconclass DE/EN - Iconographic content description (NEW) AI Prompts Used Paragraph Generation Prompt Convert the following structured information into a coherent text in German. The text contains field data that should be transformed into flowing prose while preserving all information.

IMPORTANT: - Write a MAXIMUM of 2 paragraphs - Do NOT include any URLs or web links - Do NOT include reference codes or numerical codes - Do NOT add any comments or explanations - Only output the paragraph text itself

Field: {field_name} Text: {cleaned_text}

German text (maximum 2 paragraphs): ICONCLASS Paragraph Prompt Based on the following Iconclass descriptions, write a brief German paragraph describing what the image depicts.

Descriptions: {'; '.join(descriptions)}

IMPORTANT: - Start with "Das Bild zeigt" or similar phrasing - Combine all descriptions into a flowing text - Maximum 1-2 sentences - Do NOT include iconclass codes or numbers - Do NOT include reference codes starting with "bh" - Only output the descriptive German text

German description: Example ICONCLASS Processing: Input from data: a5500: 31 A 23 1 | 31 A 25 11 | 31 B 62 11 ICONCLASS lookup (from cache): 31 A 23 1 → "standing figure" 31 A 25 11 → "arm raised upward" 31 B 62 11 → "looking upwards" AI-generated output (DE): Das Bild zeigt eine stehende Figur mit erhobenem Arm, die nach oben blickt. Translation (EN): The image shows a standing figure with raised arm, looking upwards. Translation Prompt Translate the following German text to English. Preserve the meaning and style as much as possible.

IMPORTANT: - Do NOT include any URLs or web links in the translation - Do NOT include reference codes starting with "bh" followed by numbers - Do NOT include numerical codes like 08012353 - Do NOT add any comments or explanations - Only output the translated text itself

German text: {text}

English translation: KISSKI Cluster Resources Hardware Configuration GPU: NVIDIA A100 (80GB VRAM) Architecture: Ampere Tensor Cores: 432 FP16 Performance: ~312 TFLOPS Memory Bandwidth: 2 TB/s Allocation per job: GPUs: 1× A100 CPUs: 4 cores RAM: 64 GB Time limit: 6 hours per job Job Array Configuration Array setup: Total jobs: 75 (indices 0-74) Chunk size: 400 rows per job Parallel jobs: 10 simultaneous Total rows processed: 30,000 (rows 0-29,999) Output Structure data_zeichnungen/ ├── enriched_data/ │ ├── zeichnungen_0-399.tsv # Rows 0-399 │ ├── zeichnungen_400-799.tsv # Rows 400-799 │ ├── zeichnungen_800-1199.tsv # Rows 800-1199 │ └── ... ├── images/ │ ├── {image_id_1}.jpg # IIIF thumbnail (224×224) │ ├── {image_id_2}.jpg │ └── ... └── README.md # This file Output Fields Each TSV file contains the original metadata plus AI-generated fields: Original fields: All fields from zeichnungen.tsv including: a8540 - Image ID (BILDDATEI-NR.) textobj - Original object text textfoto - Original photo text a5500 - ICONCLASS codes (primäre Ikonographie) aob26, aob28, aob30 - Relations etc. Generated fields: paragraph foto DE - German description of photograph paragraph foto EN - English translation paragraph obj DE - German description of object/artwork paragraph obj EN - English translation paragraph verwalter DE - German description of collection paragraph verwalter EN - English translation paragraph standort DE - German description of location paragraph standort EN - English translation paragraph iconclass DE - German iconographic description paragraph iconclass EN - English iconographic description KISSKI Documentation Main documentation: https://docs.hpc.gwdg.de/ GPU partitions: https://docs.hpc.gwdg.de/how_to_use/compute_partitions/gpu_partitions/ Account types: https://docs.hpc.gwdg.de/start_here/account_types/ ICONCLASS Resources Official website: https://iconclass.org/ Data repository: https://github.com/iconclass/data Help documentation: https://iconclass.org/help/lod Data Usage & Citation Source Institution: Bibliotheca Hertziana - Max Planck Institute for Art History Website: https://www.biblhertz.it/ Fotothek: https://fotothek.biblhertz.it/ AI Processing: Model: Google Gemma 2 9B Instruct Infrastructure: KISSKI (GWDG Göttingen) Processing date: November 2024 ICONCLASS: ICONCLASS classification system Data source: https://github.com/iconclass/data License: Please refer to the Bibliotheca Hertziana for source data licensing terms. Quality Notes General AI-Generated Content AI-generated texts are meant to enhance discoverability and accessibility Generated descriptions may contain inaccuracies or interpretations Always refer to original structured metadata (textobj, textfoto) for authoritative information Translations preserve meaning but may not capture all nuances of art historical terminology Generated: November 2024 Processing location: KISSKI HPC Cluster, GWDG Göttingen Contact: pietro.liuzzo@biblhertz.it