Unverified50% confidenceFactExact time
The two fix attempts—searching for the rarest word within a note and routing by paragraph before reading the whole note—both fail to change the situation, because they depend on the same search query.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
Unverified搜索结果可能因地点、设备、语言和查询措辞而异，因此单次结果不构成完整审计。67% similarUnverifiedOGAD's search tool searches text, and it does not guarantee that a broad phrase will hit all related concepts; the results of a partial search cannot be taken as evidence that a certain decision never existed; large vaults and extremely long notes have read and search limits.67% similarUnverifiedVector search can retrieve text chunks with high similarity scores, but cannot explain the reasoning logic behind answers, nor structurally connect facts scattered across different documents.66% similarUnverifiedThere are 14 notes that were never opened across 393 sessions, but two of them are in the always-loaded index, so deleting them would lose knowledge.66% similarUnverifiedThe answers to multi-hop reasoning queries cannot be derived directly from a single passage but require chained inference across two or more document segments, making standard single-round retrieval largely unsuccessful for such queries.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1018372API
curl https://kongchang.com/api/v1/knowledge/claims/1018372MCP
get_claim(id=1018372)