Unverified50% confidenceBenchmarkExact time
Agreement between the deterministic checker and blind annotators was Cohen's kappa = 0.89.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe deterministic claim-to-evidence checker certified claims with over 90% precision compared with blind annotators (78 of 85 correct).70% similarUnverifiedIn the blind review results, 96 rows showed differing interpretations of the scoring criteria.67% similarUnverifiedShopify calibrated the agreement between LLM judges and human judgment from kappa 0.02 to 0.61, while agreement between humans is 0.69.67% similarUnverifiedBlinded annotation supported 6 of the 7 findings, with defect rates between 0.53 and 1.00, whereas the random control group had a defect rate of only 0.08.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114270API
curl https://kongchang.com/api/v1/knowledge/claims/1114270MCP
get_claim(id=1114270)