Unverified50% confidenceFactExact time
The F1 score is a harmonic mean metric in classification tasks that combines precision and recall, with the formula F1 = 2 × (Precision × Recall) / (Precision + Recall)
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMacro-F1 assigns equal weight to each category by computing the F1 score for each category separately and then taking a simple average, making it suitable for scenarios with imbalanced class distributions.72% similarUnverifiedThe paper proposes the Ask-F1 metric, which comprehensively measures model performance on "when to ask" and "what to ask".61% similarUnverifiedThe modular arithmetic task is a classic benchmark for studying grokking, where the input is two integers and their operation, and the output is the result modulo some prime.59% similarUnverified每个中间推理token与输出token消耗等量的GPU算力54% similarUnverifiedHakemBench evaluates models across three dimensions—decision quality (macro F1), calibration (normalized Brier score), and selective automation (normalized area under the generalized risk-coverage curve)—and combines them into a composite score via geometric mean.53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1114479API
curl https://kongchang.com/api/v1/knowledge/claims/1114479MCP
get_claim(id=1114479)