Unverified50% confidenceFactExact time
The researchers confirmed 91 failures through manual verification and categorized them into 7 failure loci.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn tasks with propositional constraints, the proportion of models integrating candidates already verified as invalid is as high as 93%–100%.67% similarUnverifiedThe accuracy data in the test has an error margin of approximately ±8–10 percentage points at n=100 sample size (based on a 95% confidence-level binomial confidence interval).67% similarUnverifiedUsing the behavioral features of each state for failure prediction, the AUROC on the held-out set reaches as high as 0.94.66% 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.65% similarUnverified一个 90% 成功、10% 出错的工具调用系统几乎无法投入实际使用，因为单次错误会污染后续上下文造成级联失败65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946016API
curl https://kongchang.com/api/v1/knowledge/claims/946016MCP
get_claim(id=946016)