Unverified50% confidenceBenchmarkExact time
The 29-million-parameter encoder trained by the researchers achieved a popularity-weighted cross-fold AUC of only 0.486 on 985 statements, indistinguishable from the corpus prior.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter 15 training epochs on the demonstration dataset, the text classification model achieves an accuracy of 99%, with a total of 110,000 model parameters (16,000 for Attention, 33,000 for FFN, and the remainder for Embedding)67% similarUnverifiedDistillation training used 600 prompts (500 training / 100 validation), achieving a representation cosine similarity of 0.9959, a semantic correction cosine similarity of 0.9836, and a mixed-condition cosine similarity of 0.999958 relative to the teacher bridge at alpha=0.10.66% similarUnverified在20多万行的代码库中，真正活跃的可能只有2万行，其余大量是历史遗留或已废弃的逻辑66% similarUnverifiedA hand-crafted library of 22 calculators achieved perfect accuracy on the 440 cases it supported, but abstained on the remaining cases, yielding an overall coverage rate of only 40.0%.66% similarUnverifiedIn the LongMemEval benchmark, BM25 and embedding solutions converge to approximately 95% accuracy at 20 chunks66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/921814API
curl https://kongchang.com/api/v1/knowledge/claims/921814MCP
get_claim(id=921814)