English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The public release of ChatGPT has resulted in considerable publicity and hasled to wide-spread discussion of the usefulness and capabilities of generativeAI language models. Its ability to extract and summarise data from textualsources and present them as human-like contextual responses makes it aneminently suitable tool to answer questions users might ask. This paper testedwhat archaeological literature appears to have been included in ChatGPT'straining phase. While ChatGPT offered seemingly pertinent references, a largepercentage proved to be fictitious. Using cloze analysis to make inferences onthe sources 'memorised' by a generative AI model, this paper was unable toprove that ChatGPT had access to the full texts of the genuine references. Itcan be shown that all references provided by ChatGPT that were found to begenuine have also been cited on Wikipedia pages. This strongly indicates thatthe source base for at least some of the data is found in those pages. Theimplications of this in relation to data quality are discussed.

What has ChatGPT read? The origins of archaeological citations used by a generative artificial intelligence application