Unverified50% confidenceFactExact time
The research team conducted zero-shot experiments on a Brazilian disinformation dataset.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the experiments, the task resolution rate was 17% for zero-shot generation, 27% for generic self-correction, 23% for error-only feedback, and 90% for diagnostic counterexample feedback (A-CEGIS).64% similarUnverifiedIn a fraud detection task with a positive-to-negative sample ratio of 1:99, a model that predicts all samples as 'non-fraud' can still achieve 99% accuracy.63% similarUnverified以数据集为核心贡献的论文，如果数据集不公开，其贡献实质上等于零62% similarUnverifiedThe CVE-Zero test has a small sample size (n=10), and the author characterizes the results as directional.61% similarUnverifiedOpenAI's chart shows that at lower test-time compute levels, the model's success rate on this problem is close to zero, with occasional success only under extremely long reasoning chains.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/907935API
curl https://kongchang.com/api/v1/knowledge/claims/907935MCP
get_claim(id=907935)