Unverified50% confidenceBenchmarkExact time
Under preset thresholds, the hybrid matching pairwise F1 was 0.918 for account and 0.885 for contact; after calibrating thresholds separately per object, these could be raised to 0.938 and 0.963.
1
Sources
50%
Confidence
Long-term
Relevance
11/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen scanning thresholds in steps of 0.01, precision rises while recall falls, the two cross near a threshold of 0.63 (P≈0.733, R≈0.725), and the F1 peak is at a threshold of 0.41 (F1≈0.758).73% similarUnverifiedCriticGen's F1 scores on criteria-based rationales and actionable suggestions improved from 0.6369/0.5994 to 0.7554/0.7900, respectively.68% similarUnverifiedGVD achieves an F1 score of 0.97 for version family construction and an F1 score of 0.94 for rule-level consistency.67% similarUnverifiedAfter switching to an eight-token lookup table covering the space-prefixed forms, LLaVA-1.5-7B achieves F1 of 0.8221, 0.8498, and 0.8713 on the adversarial, popular, and random splits respectively; fixing the reading alone moves the adversarial split by 6.13 points.65% similarVerifiedThe F1 score is the harmonic mean of recall and precision.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1138009API
curl https://kongchang.com/api/v1/knowledge/claims/1138009MCP
get_claim(id=1138009)