{"id":"https://openalex.org/keywords/training-data-distribution","display_name":"training data distribution","description":"The statistical composition of examples used to train a machine-learning model, influencing its learning and generalization to new data.","display_name_alternatives":["distribution of training data","training dataset distribution","training set distribution"],"ids":{"openalex":"https://openalex.org/keywords/training-data-distribution","wikidata":null},"primary_topic":null,"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0852,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"works_count":401,"cited_by_count":14367,"works_api_url":"https://api.openalex.org/works?filter=keywords.id:keywords/training-data-distribution","updated_date":"2026-11-17T04:05:58","created_date":"2026-09-30T00:00:00"}
