Datasets

Reference datasets we have constructed for use in Initiative validation work. We release the full descriptions, schemas, and per-meal ground truth tables openly; the underlying photographic material is governed by the participant-consent terms documented on each dataset page.

Dataset · Released Apr 14, 2026

Weighed-Meal Reference Set v1.0 (mini-180)

A curated reference set of 180 meals prepared in a metabolic kitchen with per-ingredient weighed grams, USDA FoodData Central entry mappings, and computed kcal ground truth. Meals are stratified across three cuisine buckets (Western, East Asian, Mediterranean). Tabular data published openly; photographic material released under restricted access by participant consent.

Dataset · Released Mar 27, 2026

Restaurant Pilot Meal Set (N=32, pilot)

A pilot dataset of 32 restaurant-served meals with reference kcal values derived either from published chain-restaurant nutrition disclosures (verified by dismantle-and-weigh) or from dietitian-led recipe reconstruction. Released as a companion to the restaurant-extension preprint (DAI-PRE-2026-02); not yet a full reference set.

Dataset · Released Feb 18, 2026

Cuisine Classification Codebook v1.1

A coding manual for assigning meals to cuisine buckets in dietary assessment research. Defines six buckets, provides worked examples and decision rules, specifies a two-rater plus adjudicator procedure, and reports inter-rater reliability (Cohen's kappa) from the Initiative's internal calibration.