AI Crypto Data Sources: How Every CMC AI Answer Is Attributed

Key Takeaways

• A source is identified by its URL, which is also its identity key, so the list is deduplicated on the normalised URL rather than on a title.
• Source concentration is high and varies sharply by question type. On the discussion question, 84% of linked sources were posts on x.com. Measured across four question types, x.com accounts for 51%.
• Those 206 links resolved to just 13 distinct hostnames, so the source base is concentrated rather than broad.
• The API returns sources_count, the true total behind an answer, next to a capped sources[] array and a sources_truncated flag.
• Requesting sources_limit=0 still returns sources_count, so a citation count can be displayed without transferring the array.

What a Source Is

The source object is deliberately thin. Its one required field is the canonical URL of the page a claim came from, and because that URL is the only field, it is also the identity used to deduplicate. Two entries pointing at the same article, arriving with different query strings, are the same source and collapse into one.

That puts weight on URL normalisation, which the documentation describes as forcing https, stripping tracking and rendering parameters, stripping www., normalising twitter.com to x.com, and removing fragments before the array is deduplicated. Across the 206 published source links measured, every one used https and none carried a query string, so scheme forcing and parameter stripping both hold on the rendered surface.