Unverified50% confidenceBenchmarkExact time
Cohen's kappa reaches 0.964 on boundary-matched spans, but drops sharply to a macro F1 of 0.753 after incorporating missed entities, boundary errors, and label corrections.
1
Sources
50%
Confidence
Long-term
Relevance
9/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGVD achieves an F1 score of 0.97 for version family construction and an F1 score of 0.94 for rule-level consistency.69% similarUnverifiedCriticGen's F1 scores on criteria-based rationales and actionable suggestions improved from 0.6369/0.5994 to 0.7554/0.7900, respectively.65% similarUnverifiedThe stopword-removal-only configuration can achieve a token reduction of 29.6% while maintaining a BERTScore-F1 of 0.91365% similarUnverifiedIn the BioPhys-Bridge evaluation, DeepSeek-V4-Flash achieved the highest score with an evidence ID F1 score of 0.360.64% similarUnverifiedIn the BioPhys-Bridge evaluation, Qwen3.7-Max's evidence ID F1 score is 0.316.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/942791API
curl https://kongchang.com/api/v1/knowledge/claims/942791MCP
get_claim(id=942791)