Unverified50% confidenceBenchmarkExact time
The OCR model achieves an F1 score of 87% on a real invoice dataset.
1
Sources
50%
Confidence
Long-term
Relevance
9/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe framework achieved a precision of 0.82, a recall of 0.85, and an F1 score of 0.82.67% similarUnverifiedThe model's F1 score is 72%, and the data has a severe class imbalance with a ratio of 89:11.66% similarUnverifiedOn TruthfulQA, 8-bit scored 85.6%, slightly higher than OQ4E's 84.8%.61% similarUnverifiedUnder the leave-one-author-out cross-validation setting, the strongest model achieved an accuracy of 81.42%.60% similarUnverifiedThe best F1 scores for sarcasm detection tasks on standard datasets (such as iSarcasm and the SemEval series) have long hovered in the 70%–80% range.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961136API
curl https://kongchang.com/api/v1/knowledge/claims/961136MCP
get_claim(id=961136)