Unverified50% confidenceFactExact time
Jev works by having users predefine the set of allowed answers, and Jev returns a label, a score, or a yes/no probability value.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedJev offers three question types: Select, Score, and Null/Bool, with each response accompanied by a confidence value.74% similarUnverifiedJev's core mechanism is to extract and number the currently interactive elements into a list, having the model only answer what to do and which number to select, rather than guessing coordinates or writing selectors.71% similarUnverifiedJev receives request content, candidate models, and their capability descriptions, and returns structured selection rationale via the TypeSafe Choice interface.70% similarUnverifiedJev is a pure classifier that has not been trained to generate text; given a set of candidate options, it outputs a choice with a confidence score.70% similarUnverifiedSearch reranking is one application scenario for Jev: first use inexpensive algorithms such as BM25 to retrieve candidate results, then use Jev to score the candidates for relevance.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1052181API
curl https://kongchang.com/api/v1/knowledge/claims/1052181MCP
get_claim(id=1052181)