Source Selection
How a system decides which sources are worth using.
Industry Term
Full explanation
Source selection is how a search or AI system decides which of the available sources are relevant and trustworthy enough to use when constructing an answer.
Selection criteria vary by system but commonly weigh topical relevance, apparent authority or expertise, recency, and how well a source's structure lets the system extract a clean answer. A source can be accurate and still be passed over if a competing source states the same fact more clearly or is judged more authoritative on the topic.
Source selection is the decision point that sits after Retrieval and before Citation: a system may retrieve dozens of candidate sources but select only a handful to actually cite or draw from in the final answer.
Why this matters
It reframes the strategic question from how to rank to why a system would choose this source over another, which is a far more useful thing to work on.
Example
Three sources all correctly state a product's return policy. A system selects the one from the brand's own help center over a forum post and a comparison site, because it reads as the more authoritative, directly relevant source for that specific fact.
Where this sits
Source Selection belongs to Retrieval, Evidence & Consensus, one of the seven layers of the Aingworth Glossary. Information exists, then it is retrieved, then sources are selected, then they corroborate one another, then consensus emerges. This is where Aingworth's Consensus Over Rankings thesis lives.
Related terms
Ready to see where your brand stands?
Start with the free diagnostic to see which condition of the Recognition Triangle is leaking, or read the frameworks these terms belong to.