Unverified50% confidenceFactExact time
Clairic is a zero-output-token extraction model that returns one value per field in a single forward pass and does not generate text.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA response with zero output tokens does not mean no inference occurred, because the model completed a full encoding and forward computation, only outputting structured options rather than generating verbatim.75% similarUnverifiedZero-shot extraction requires no labeled samples and can directly extract the corresponding values based solely on field definitions or Schema descriptions.66% similarUnverifiedToken consumption includes both the input content and the output returned by the model.64% similarUnverifiedZero-shot models require no labeled data; simply writing out labels in natural language is enough to produce classification results.62% similarUnverifiedAt temperature: 0, sampling degenerates to greedy decoding, and given the same model weights and input token sequence, the decoding path is fully deterministic.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1075158API
curl https://kongchang.com/api/v1/knowledge/claims/1075158MCP
get_claim(id=1075158)