Unverified50% confidenceBenchmarkExact time
Of the 69 artificially injected document problems (wrong check digits, unregistered numbers, deregistered issuers, other people's numbers, wrong tax amounts), all 69 were routed to manual review, and 95.7% were caught by the corresponding validations.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBy re-tallying the results files, readers found a row of data that the authors had skipped: the maintainer file lists 9 of 212 tests judged WEAK (4%), while the agent file lists 79 of 591 (13%).74% similarUnverifiedFor an invoice classification model with 97% accuracy, when a reviewer examines 300 invoices per day, only about 9 will be wrong, and errors are buried among correct items, causing the reviewer's rejection rate to approach zero.71% similarUnverifiedResearch shows that approximately 88% of enterprise spreadsheets contain errors.70% similarUnverifiedOn the real registry (2.58 million companies, all passing the check digit), for each of 300,000 registered numbers one digit was corrupted: the check digit caught 95.6%, the query caught 4.1%, and 0.29% would land on another real company.70% similarUnverifiedIn 11 of the 12 models, between 87.5% and 100% of capitulation cases stopped at the exact wrong number provided by the user, meaning capitulation typically involves switching sides entirely.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036986API
curl https://kongchang.com/api/v1/knowledge/claims/1036986MCP
get_claim(id=1036986)