Unverified50% confidenceBenchmarkExact time
In batch mode, the macro F1 scores of JEV and Qwen on TrialGPT were 0.652 and 0.660, respectively.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCriticGen's F1 scores on criteria-based rationales and actionable suggestions improved from 0.6369/0.5994 to 0.7554/0.7900, respectively.65% similarUnverifiedUnder the best configuration, NARS achieved F1=0.57 and AUC=0.56, outperforming zero-shot Qwen3.6:27B and GPT-oss:20B.65% similarUnverifiedCompared with v1.2, v1.5 improves the F0.5 for real spelling errors from 0.882 to 0.963 and the F0.5 for missing words from 0.078 to 0.698; tense errors remain a weak point, with an F0.5 of only 0.119.64% similarUnverifiedStandard Jev achieves an average macro-F1 of 62.93%, while the strongest LLM baseline achieves 67.28%.63% similarUnverifiedGVD achieves an F1 score of 0.97 for version family construction and an F1 score of 0.94 for rule-level consistency.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1103056API
curl https://kongchang.com/api/v1/knowledge/claims/1103056MCP
get_claim(id=1103056)