Unverified50% confidenceFactExact time
joey-1's outputs consist of calibrated probabilities rather than text.
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe confidence number a model reports about itself and a calibrated probability are not the same kind of object: the self-reported number comes from token sampling in the same forward pass as the answer, with no lookup of outcomes, whereas a calibrated probability must come from a paired record (join) of predictions and outcomes.69% similarUnverifiedThe model's output tokens are zero, because it only returns probabilities rather than generating text.66% similarUnverified马尔可夫头仅需记录前一个token状态即可推导下一token修正概率，参数量通常不超过原模型的0.1%63% similarUnverifiedThe verification process in traditional speculative decoding accepts draft-proposed tokens with probability min(1, p(x)/q(x)), and upon rejection resamples from the corrected distribution norm(max(0, p(x)-q(x))), which can be proven to produce a token distribution identical to directly sampling from the target model (lossless).62% similarUnverifiedAblation experiments and behavioral analysis show that the tokens saved by DoubtLess mainly come from after the first appearance of the correct answer.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1113332API
curl https://kongchang.com/api/v1/knowledge/claims/1113332MCP
get_claim(id=1113332)