Expired50% confidenceFactExact time
OpenAI's web retrieval implementation typically comprises four stages: query rewriting, vector or keyword retrieval, content truncation and reranking, and final generation
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/6/2026(expired)
Sources
拆解ChatGPT选源机制：网络流量分析揭示AI引用真相
hackernewshackernews7/6/2026
Related Claims
VerifiedBrowseComp is an agentic search benchmark proposed by OpenAI that evaluates a model's ability to complete multi-step information retrieval and integration in a real web environment75% similarUnverifiedWhen tasks are concentrated on web operations, OpenAI Operator or open-source frameworks combined with DOM parsing often provide a better success rate.69% similarUnverifiedUsing structured documentation generated by OpenWiki as the knowledge source for a vector retrieval library can further improve AI retrieval accuracy in large codebase scenarios.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/232105API
curl https://kongchang.com/api/v1/knowledge/claims/232105MCP
get_claim(id=232105)