Unverified50% confidenceTradeoffExact time
For misreads of text fields, there are different conventions such as counting only FN, only FP, or both FN and FP; different conventions directly change the final score, so the convention adopted must be stated when publishing results.
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFwrd's SMS filtering logic is "qualifying", so not all text messages will be forwarded; the specific filtering must be configured according to the official guide, and misjudgments may occur.69% similarUnverifiedThe writable field set mechanism separately declares which fields are writable, and writes beyond the declared set should be rejected outright rather than truncated.65% similarUnverifiedAppendix F of the paper provides a pseudo-text window: each latent-space step can be mapped to the nearest token embedding, and the readability score is taken as the mean of the best cosine match over the vocabulary.63% similarUnverifiedFTS5 依赖字面匹配，当查询词与存储内容用词不同但语义相近时可能漏检，是纯全文方案的固有局限63% similarUnverifiedThe underlying implementation of constrained decoding relies on finite state machines (FSM) or context-free grammars (CFG).61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1100171API
curl https://kongchang.com/api/v1/knowledge/claims/1100171MCP
get_claim(id=1100171)