Unverified50% confidenceBenchmarkExact time
Test condition S0 uses approximately 2,500 words of raw material; S1 adds administrative context to expand to approximately 9,800–9,900 words; S2 adds outdated or similarly scoped distractor records with the same word count as S1.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the held-out test set, FakeSpotter achieved a macro F1 score of 0.788 for short texts and 0.793 for long texts.58% similarUnverifiedLLaMA 2的32000词表在4096维隐层下嵌入层需占用约1.3亿参数58% similarUnverifiedOn the S-words task, the model achieves an R² of 0.8 and an NRMSE of 0.08.57% similarUnverifiedOn a fixed revision of the repository, Praxa passed 1,027/1,027 unit tests and 89/89 Workerd tests, instrumented all 363 expected source files, and met four coverage lower bounds, though raw per-test records and independent reproduction are not yet available.56% similarUnverifiedCFC基准的历史序列涵盖V1至V100，最终发布的可复现测试集包含95个变体、共计285次重复运行55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003831API
curl https://kongchang.com/api/v1/knowledge/claims/1003831MCP
get_claim(id=1003831)