Unverified50% confidenceFactExact time
A page that was never indexed and a page that was indexed and later removed share the same metadata and the same determination, but their causes differ: the former has not yet been judged, while the latter has been judged and failed.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAt the database level, an empty-result query cannot be distinguished from a negative result: a SELECT returning zero rows may mean the table truly has no matching records, or that the table is deprecated, the field has been migrated, or the query condition was written incorrectly.67% similarUnverifiedFailed queries should be stored as 'error' rather than 'not included', and the indexing rate should only be calculated over URLs that actually received an answer, to prevent errors from being misread as the site being dropped.66% similarUnverifiedA skip request is rejected if any field is missing, if the results of two runs are consistent, or if the basis for the determination has been modified by the same patch66% similarUnverifiedCitation decay monitoring needs to distinguish two phenomena: first, retrieval-layer loss, i.e. the page is no longer included in the retriever's candidate set; second, generation-layer replacement, i.e. the page is still retrieved, but the model chose other sources as citations when synthesizing the answer.66% similarUnverifiedA reliable way to distinguish an empty-result query from a negative result is to introduce a positive control: run the same query with a record you are sure exists; if the control also returns zero rows, the query itself is broken.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1052415API
curl https://kongchang.com/api/v1/knowledge/claims/1052415MCP
get_claim(id=1052415)