Unverified50% confidenceBenchmarkExact time
On the internal test set (11,773 AI-involved files and 2,541 human files), the method achieved a macro F1 of 72.4 at the 1% false positive rate operating point.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/21/2026
First Seen
Valid until: 1/19/2027
Sources
Related Entities
Related Claims
UnverifiedA benchmark released by anyformat shows its parsing quality score is 78.1%, while Google Document AI's is 55.0%.74% similarUnverifiedIn EvoMap's benchmark test, on 563 questions using the same AI model, a single agent working independently achieved a 26% accuracy rate, while swarm collaboration mode achieved 71%.73% similarUnverifiedOn a test set of 600 synthetic invoices, the QLoRA fine-tuned model achieved a full-invoice exact rate of 83.0%, an auto-approval rate of 86.8%, and 0 out of 461 validation-coverage field errors in approved invoices (upper bound 0.8%).72% similarUnverifiedThe team's first study collected about 95,000 pieces of AI-cited content and decomposed 189 factors, but it was overturned due to problems such as p > n, using in-sample data for evaluation, and using globally random negative samples; after query-level out-of-fold re-measurement, R² = −0.31.71% similarUnverifiedAn evaluation suite with 1,800 test cases has long maintained a stable aggregate pass rate of 97%, but the 64-case multilingual slice within it has a pass rate of only 61%71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079468API
curl https://kongchang.com/api/v1/knowledge/claims/1079468MCP
get_claim(id=1079468)