Unverified50% confidenceBenchmarkExact time
In the benchmark test, the heuristic peak rule achieved 93.3% overall accuracy, 100.0% impact recall, and 38.4% cadence false positives, requiring manual threshold tuning.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedIn the benchmark test, Logistic Regression achieved 86.7% overall accuracy, 100.0% impact recall, and 0.0% cadence false positives.78% similarUnverifiedThe entire test session (including a large number of Ultra and Max mode tasks) consumed only approximately 3% of the usage quota (dropping from 98% to 95%), indicating good token efficiency.77% similarUnverifiedEvidence-driven pre-improvement validation improved precision from 58.6% to 72.3%, and reduced unsupported objectives per round from 1.93 to 0.50.76% similarUnverifiedActionable Agent evaluation thresholds include a task decomposition rate and tool selection accuracy of 90% or above, a closed-loop completion rate of no less than 85%, and an error recovery rate of no less than 80%.76% similarUnverifiedAfter disabling schema constraints and authentication, the erroneous backend dispatch rate spiked from 0% to 95.28% in replay/test evaluations.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1007779API
curl https://kongchang.com/api/v1/knowledge/claims/1007779MCP
get_claim(id=1007779)