OpenAI's official API documentation confirms its models are trained to emit internal citation markers meant to be stripped before a response reaches an end user

openaicitation-formattingchatgptai-tellsmachine-text-forensicsapi-documentation

OpenAI's "Citation Formatting" guide, part of its official API documentation, describes a citation-marker syntax that model outputs carry internally and that a calling application is expected to parse out before showing a response to a user. The guide recommends a marker syntax built from private-use-area Unicode characters (U+E200, U+E202, U+E201) — CITATION_START, CITATION_DELIMITER, and CITATION_STOP — wrapping a citation family and source ID (e.g. {CITATION_START}cite{CITATION_DELIMITER}turn0file1{CITATION_STOP}), and states plainly why: "These citation markers are highly recommended because they closely match the markers our models are trained on." The guide's own parsing instructions confirm the markers are not meant for end-user display: "Once the model emits citations, you need to extract them from the response text so you can resolve source IDs, render links, or remove the raw markers before showing the answer to users."

This is a Tier 1, OpenAI-authored primary source for the general mechanism class behind the 'oaicite' forensic claim about the 2025 MAHA report: OpenAI models do carry internal citation-placeholder tokens designed to be stripped by downstream processing before a user sees the output, and a substitution failure would leak raw marker text into visible text — exactly the failure mode entity-oaicite names. It does not, however, confirm the specific string "oaicite" itself; see claim-openai-cite-marker-name-not-oaicite and question-verify-oaicite-chatgpt-internal-citation-marker.