Unverified50% confidenceFactExact time
Perplexity cited these spam pages as information sources when answering user questions.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
UnverifiedPerplexity not only retrieves pre-built indexes but can also crawl web content in real time.70% similarUnverifiedPerplexity的引用通常指向网页而非经过同行评审的学术数据库69% similarUnverifiedReliably mapping web pages into a fixed schema is a longstanding difficult problem in the NLP field, and errors in field extraction, omissions, and hallucinations can contaminate query results65% similarUnverifiedGlobal queries can answer inductive questions requiring a macro perspective (such as the main themes across an entire document set), a scenario that pure vector retrieval is almost incapable of handling.64% similarVerifiedThe "answer engine" paradigm represented by Perplexity abandons returning lists of web pages and instead directly generates natural language answers with cited sources, which is essentially the productization of RAG technology.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/909817API
curl https://kongchang.com/api/v1/knowledge/claims/909817MCP
get_claim(id=909817)