{"slug": "a-framework-for-recipe-data-structure-with-applications-for-culinary-and", "title": "A framework for recipe data structure with applications for culinary and nutritional insights", "summary": "Researchers at IIIT-Delhi's Complex Systems Laboratory released RecipeDB2, a structured compilation of 128,942 recipes and 35,474 ingredients spanning 32 regions and 99 countries, according to a new arXiv paper (2609.22099v1). The framework parses ingredient phrases into seven culinary attributes with a transformer-based named-entity model, links ingredients to USDA reference tables via a BERT embedding strategy that scored F1 = 87.90 on a manually adjudicated set of the 200 most frequent ingredients, and yields 148 nutritional parameters per mapped ingredient. A Random Forest classifier propagates 34 ingredient categories across the full vocabulary, and a deterministic rule set assigns each recipe a dietary style, making culinary heritage computable for nutritional and geo-cultural analysis.", "body_md": "arXiv:2609.22099v1 Announce Type: new \nAbstract: Cooking is a complex process that transforms raw ingredients into delicious and nutritious dishes, yet the recipes that encode this process remain largely free text; readable by people but not directly computable. Existing recipe collections capture fragments of this information, but no shared representation links a recipe's structured ingredient composition, its geo-cultural provenance, and its nutritional profile within a single queryable schema. We address this representation gap by formalizing a framework for recipe data structure that decomposes each recipe into typed ingredient entities, grounds those entities in a reference nutritional database, and annotates them with geo-cultural and dietary context. We present RecipeDB2, a structured compilation of 128,942 recipes with 35,474 ingredients from 32 regions and 99 countries. Ingredient phrases are parsed into seven culinary attributes using a transformer-based named-entity model; ingredients are linked to the USDA reference tables through a BERT embedding strategy (F1 = 87.90 on a manually adjudicated set of the 200 most frequent ingredients), yielding 148 nutritional parameters per mapped ingredient; a Random Forest classifier propagates 34 ingredient categories across the full vocabulary; and a deterministic, conservative rule set assigns each recipe a dietary style. Through RecipeDB2 (https://cosylab.iiitd.edu.in/recipedb2/), we demonstrate a scalable framework for making recipes computable, turning culinary heritage (long treated as an artistic rather than a quantitative object) into a data-driven analysis.", "url": "https://wpnews.pro/news/a-framework-for-recipe-data-structure-with-applications-for-culinary-and", "canonical_source": "https://arxiv.org/abs/2609.22099", "published_at": "2026-09-22 04:00:00+00:00", "updated_at": "2026-09-22 04:25:16.061023+00:00", "lang": "en", "topics": ["machine-learning", "natural-language-processing", "ai-research", "structured-data"], "entities": ["RecipeDB2", "IIIT-Delhi", "USDA", "arXiv", "BERT", "Random Forest"], "alternates": {"html": "https://wpnews.pro/news/a-framework-for-recipe-data-structure-with-applications-for-culinary-and", "markdown": "https://wpnews.pro/news/a-framework-for-recipe-data-structure-with-applications-for-culinary-and.md", "text": "https://wpnews.pro/news/a-framework-for-recipe-data-structure-with-applications-for-culinary-and.txt", "jsonld": "https://wpnews.pro/news/a-framework-for-recipe-data-structure-with-applications-for-culinary-and.jsonld"}}