Generative Artificial Intelligence creates delicious, sustainable, and nutritious burgers

Classic rediscovery and novelty

• SDS = 0 identifies a match with a reference recipe, while SDS > 0 quantifies novelty; the model rediscovered the Big Mac and generated increasingly novel delicious burgers.Delicious Burger 1 had SDS = 3 and Delicious Burger 2 had SDS = 6, while retaining familiar burger structure.Source: Results · p. 2, Discussion · p. 7
• Delicious Burger 1 exceeded the Big Mac in flavor, and Delicious Burger 2 exceeded it in overall liking and flavor, while both had statistically similar texture ratings.The blinded sensory evaluation included 101 participants.Source: Results · p. 3

Nutrition and personalization

• The Nutritious Burger achieved a healthy eating index of 63.12 versus 33.71 for the Big Mac while reducing environmental impact by a factor of six.Its improved profile included more vegetables, whole grains, and plant protein, alongside less refined grains, sodium, and saturated fat.Source: Results · p. 5, Discussion · p. 7

Model validation

• The model captures higher-order burger-design regularities, including ingredient co-occurrence, recipe length, and quantity distributions.It learns latent structure directly from large-scale human-generated recipes rather than reproducing only superficial statistics.Source: Results · p. 2, Discussion · p. 5

Implications and limitations

• The study defines food formulation as a quantitative, data-driven design process that uses recipes to navigate measurable taste, nutrition, and sustainability objectives.The authors frame recipes as a human-centered interface between culinary tradition and artificial intelligence.Source: Discussion · pp. 6, 8, Conclusion · p. 8
• The model inherits biases from existing recipes, omits processing and cooking transformations, relies on aggregated environmental and nutritional data, and was tested on limited burgers and participants.The authors state that broader studies are needed to establish generalizability across populations and contexts.Source: Discussion · pp. 7–8

• The study presents generative artificial intelligence for creating delicious, sustainable, and nutritious burgers.Source: Supplementary File 1 · p. 14
• Vahidullah Tac, Christopher Gardner, and Ellen Kuhl are listed as the authors.Source: Supplementary File 1 · p. 14

• Burger recipes are identified using both recipe names containing “burger” and a large language model’s classification, requiring both signals for inclusion.Source: Identifying burger recipes · p. 14
• Ingredient descriptions are parsed into ingredient name, quantity, and unit, then normalized into numeric quantities and standardized measurements.Source: Parsing burger ingredients · p. 14
• 522,517 recipes from the combined food.com database yielded 3,882 identified burger recipes for training-data construction.Source: Data preparation · p. 14, Table 1 · p. 15
• Manual review corrects parsed inconsistencies, producing a curated dataset of 3,882 recipes with 3,683 unique ingredients and 171 measurement units.Source: Parsing burger ingredients · p. 15
• Ingredient names are consolidated by removing descriptors, merging related products, correcting spellings, and filtering rare ingredients.Source: Unifying ingredient names · pp. 15–16
• Measurements are converted to grams, ingredient volumes to weights, and recipes are normalized to 500 kcal before storage as a 2,216 × 146 ingredient-weight array.Source: Converting units of measurement into… · p. 16, Processing ingredient quantities · p. 16

• A burger recipe is represented as a selection of ingredients and their quantities, with 146 unique ingredients available.Source: Modeling · p. 16, Table 2 · p. 17
• The two-stage approach first identifies ingredients with a mask model and then predicts their quantities with a value model.Source: Modeling · p. 17
• Multinomial diffusion models the discrete ingredient mask, while a score-based generative model models continuous ingredient weights.Source: Modeling · p. 17
• The training data contains 2,216 recipes, and ingredient-frequency and weight distributions summarize its most-used ingredients.Source: Figure 1 · p. 18, Figure 2 · p. 18
• The multinomial diffusion process repeatedly resamples categorical ingredient states, with β_t controlling the chance of uniform resampling.Source: Mask model · p. 18
• The score-based model learns a conditional distribution of ingredient weights given the recipe mask using forward noising and reverse denoising processes.Source: Value model · pp. 19–20

• The mask model uses an embedding layer and three fully connected layers of 512 neurons each, trained for 100,000 epochs.Source: Training and validation · p. 20
• The value model uses four hidden layers of 256 neurons each and is trained for 20,000 epochs.Source: Training and validation · p. 20
• The value-model dataset is split into 80% training and 20% validation data.Source: Training and validation · p. 20

Rediscovering the Big Mac®

• The Big Mac® benchmark is approximated as a 500 kcal recipe containing seven ingredients with specified quantities.The estimated formulation includes 81 g ground beef, 74 g bun, 32 g mayonnaise, 27 g pickle, 27 g onion, 21 g lettuce, and 18 g cheese.Source: Rediscovering the Big Mac® · p. 20, Figure 3 · p. 20
• The Substantial Difference Score compares recipes using ingredient presence and quantity ratios, with SDS = 0 defining a match and SDS > 0 indicating novelty.The score is the sum of binary ingredient-level distances across the database.Source: Substantial Difference Score · p. 21

Sustainability

• Environmental impact scores combine land use, greenhouse gas emissions, eutrophication potential, and scarcity-weighted water use into ingredient- and recipe-level sustainability measures.Ingredient impacts are mapped from a 146-ingredient model onto environmental database categories and aggregated using ingredient quantities.Source: Environmental Impact Score · p. 21, Figure 4 · p. 22, Table 3 · p. 23

Nutrition

• Nutrition-based selection identifies repeated recipes in the 90th and 95th percentiles of the Healthy Eating Index and balanced hybrid nutrient density score distributions.The supplementary figures include bean-corn blends and alternative formulations selected by HEI and bHNDS, as well as recipes personalized to individual demographic and activity profiles.Source: Healthy Eating Index · pp. 22–24, Figure 6 · p. 24, Figure 7 · p. 24
• A personalized nutrient profiling model generates burger recipes tailored to differences in age, sex, body composition, physical activity, and physiological status.The examples cover sedentary adults, a very active adolescent, and a moderately active older adult.Source: Personalized nutrition · p. 25, Figure 8 · p. 25

Sensory evaluation

• The sensory evaluation enrolled voluntary participants from the general population to assess all six burgers in a restaurant setting.Participants evaluated burgers after answering background questions.Source: Sensory evaluation · p. 28, Figure 1 · p. 28
• Participants rated overall liking, flavor, and texture on 7-point Likert scales and reported selected flavor and texture attributes.The survey also collected demographic, dietary, purchasing, and food-priority information.Source: Sensory evaluation · p. 28, Figure 1 · p. 28

Survey design

• The supplementary materials classify respondents by age, gender, education, dietary preference, burger consumption frequency, grocery purchasing habits, and food priorities.Food priorities included health, price, taste, convenience, familiarity, environment, and animal welfare.Source: Sensory evaluation · p. 28, What is your age? · p. 29, Which gender do you identify as? · p. 29

Blinding and preparation

• The six burgers were prepared and photographed before sampling, with Sustainable Burger 1, Delicious Burger 1, and the Nutritious Burger assigned blinded labels 413, 674, and 491.The sensory evaluation took place at an active restaurant.Source: Figure 1 · p. 28, Sensory evaluation · p. 28

Liking

• Overall liking was measured on a 7-point scale ranging from “Like very much” to “Dislike very much.”Source: How would you rate your overall liking… · p. 30, How would you rate the flavor of… · p. 30

Flavor

• Flavor feedback included attributes such as meaty, off-flavor, bland, earthy, smoky, sweet, salty, fatty, savory, and good aftertaste.Source: Please check all the words or phrases… · pp. 30–31

Texture

• Texture feedback included attributes such as chewy, crispy or crunchy, crumbly or grainy, firm, soft, moist, dry, tough, fibrous, gummy, and sticky.Source: Please check all the words or phrases… · p. 31

Demographics

• The 101 participants were distributed across age groups, with 22% aged 18–25 and 16% older than 55.The remaining participants were distributed across the 26–35, 36–45, and 46–55 age groups.Source: Population demographics · p. 31
• Participants were 47.5% male, 47.5% female, 3% non-binary, and 2% who preferred not to say.Source: Population demographics · p. 31

Dietary preference

• Dietary preferences comprised 65% omnivores and 35% flexitarians.Source: Population demographics · p. 31

• The study includes five burgers, with each burger’s ingredients and quantities provided for chef development.Source: Recipes · p. 33
• The first burger list specifies beef, bun, ketchup, lettuce, mayonnaise, onion, cheese, pickle, and tomato.Source: Delicious Burger 1 · p. 33
• The second burger list specifies beef, brown sugar, bun, garlic, onion, cheese, sauce, thyme, tomato, and Worcestershire sauce.Source: Delicious Burger 2 · p. 33
• The third and fourth lists specify mushroom-based recipes, respectively using arugula, mayonnaise, mustard, oil, portobello, rosemary, and garlic, or bacon, beef, cheddar, ketchup, mushroom, onion, and pepper.Source: Sustainable Burger 1 · p. 34, Sustainable Burger 2 · p. 34
• The fifth list specifies a bean-based recipe containing bun, cilantro, cornflour, cumin, egg, jalapeno, oats, oil, onion, oregano, and black pepper.Source: Nutritious Burger · p. 34

• Chefs must develop recipes with the listed ingredients and amounts without adding or removing ingredients.Source: Guidelines · p. 34
• Processing steps are left to the chefs, and singular ingredient labels are used for convenience.Source: Guidelines · p. 34
• Chefs should adjust salt to taste, record the amount used, and may discard peels, stems, sautéing oil, or aromatic herbs after use.Source: Guidelines · p. 35
• Overflowing burgers are acceptable, but chefs are asked to prepare presentable burgers with structural integrity.Source: Guidelines · p. 35
• Chefs may choose ingredient varieties, interpret beef as intact meat or ground beef, and select suitable options for unspecified cheese or sauce categories.Source: Guidelines · p. 35

• The document gives AI-generated ingredient lists, their quantities, preparation steps, and photographs of the chef-assembled burgers.Source: Recipes with ingredients and… · p. 36
• It also includes the Big Mac ingredient list while using a purchased Big Mac for the survey’s authentic comparison experience.Source: Recipes with ingredients and… · p. 36

Big Mac®

• The Big Mac benchmark contains ground beef, bun, mayonnaise, pickle, onion, lettuce, and cheese, and was purchased rather than chef-prepared for sensory authenticity.Source: Purchased product · p. 36, List of ingredients · p. 36, Figure 1 · p. 37

Delicious burgers

• Delicious Burger 1 uses ground beef, bun, ketchup, lettuce, mayonnaise, onion, cheese, pickle, and tomato.Source: List of ingredients · pp. 36–37, Figure 2 · p. 37
• Delicious Burger 2 combines beef with brown sugar, garlic, onion, Gruyere cheese, remoulade, thyme, tomato, and Worcestershire sauce.Source: List of ingredients · p. 38, Figure 3 · p. 38

Sustainable burgers

• Sustainable Burger 1 is a portobello mushroom burger with bun, garlic, mayonnaise, mustard, oil, rosemary, and salt.Source: List of ingredients · p. 39, Preparation instructions · p. 39, Figure 4 · p. 39
• Sustainable Burger 2 combines bacon, ground beef, brioche bun, cheddar, ketchup, crimini mushroom, onion, pepper, and salt.Source: List of ingredients · pp. 39–40, Preparation instructions · p. 40, Figure 5 · p. 40

Nutritious burger

• The Nutritious Burger is bean-based and includes kidney beans, bun, cilantro, corn flour, cumin, egg, jalapeno, oats, oil, onion, oregano, pepper, and salt.Source: List of ingredients · pp. 40–41, Preparation instructions · p. 41, Figure 6 · p. 41