Unverified50% confidenceBenchmarkExact time
完全不给文章时，Fiorillo v0.5 的宏观 F1 骤降至 0.4384，说明模型依赖正文内容
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
Unverified只给标题就能把 Fiorillo v0.5 的 F1 提升 0.0939，可能存在从标题泄露答案的成分78% similarUnverified在边界匹配的片段上 Cohen's kappa 达到 0.964，但纳入遗漏实体、边界错误和标签修正后宏观 F1 骤降至 0.75368% similarUnverifiedAccording to the MedViT paper, the model achieved a Macro F1 score of 0.7791 on ChestX-ray1465% similarUnverified在留出测试集上，FakeSpotter对短文本取得0.788的宏观F1分数，对长文本取得0.793的宏观F1分数65% similarUnverified仅停用词移除配置可实现token削减29.6%，BERTScore-F1保持在0.91364% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/983041API
curl https://kongchang.com/api/v1/knowledge/claims/983041MCP
get_claim(id=983041)