Unverified50% confidenceFactExact time
Three question types are used in the decision model evaluation: choice (returns options and probabilities), noul (returns a yes/no probability from 0 to 1), and score (returns a score within a custom range); the type name for noul is not boolean, as the API rejects boolean.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe Jev model breaks down judgment tasks into three answer types: noul (yes/no judgment), choice (multi-class classification), and score (graded scoring).61% similarUnverifiedThe Decisions API directly returns typed results, including probability values, options, and scores61% similarUnverifiedCLM replicates Jev's "System One" decision interface and supports three core question primitives: Choice (returns a categorical probability distribution), Noul (outputs calibrated true/false probabilities), and Score (scores according to a rubric).60% similarUnverifiedDecision models focus on answering yes/no judgments, multiple-choice questions, and probability-scored rating-type problems.59% similarUnverifiedThe Adjudicated Query pattern externalizes judgment logic to a deterministic rules engine, thereby avoiding the problems of approximate matching in vector retrieval and the non-reproducibility of probabilistic sampling in LLMs.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/998802API
curl https://kongchang.com/api/v1/knowledge/claims/998802MCP
get_claim(id=998802)