IDEArq Bibliographic Corpus: Archaeological Publications of the Iberian Peninsula

Dataset of 1,181 archaeological publications covering the Iberian Peninsula from the Paleolithic to the Iron Age, collected from the IDEArq (Spatial Digital Infraestructure) (http://www.idearqueologia.org). The corpus includes academic articles, book chapters, and conference proceedings published between 1915 and 2024, in five languages: Spanish (55%), English (33%), Portuguese (6%), Catalan (4%), and French (1%). Each entry is indexed with SCImago Journal Rank (SJR) subject categories where available, enabling disciplinary filtering. This dataset served as the document base for a Retrieval-Augmented Generation (RAG) evaluation pipeline using local language models via Ollama.