Unverified50% confidenceBenchmarkExact time
Under a confidence gate of τ=0.6, Largha-150M-v1 escalated 45.0% of official-set decisions, reducing LLM calls by 55.0%, raising the retained-subset accuracy from 0.906 to 0.9936, with an overall routing accuracy of 0.8135.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedVERGE improved precision from 0.764 to 0.849 and Matthews Correlation Coefficient from 0.681 to 0.73071% similarUnverifiedOn accuracy: τ=0.4 is 0.7305, the hosted single run is 0.7085, the local single run is 0.7320, and τ=0.6 is 0.7115.68% similarUnverifiedIn the DistilBERT-to-DistilBERT configuration on the SST-2 dataset, the reliability-gated method achieved 88.800±0.532%, RAPID achieved 88.685±0.462%, both improving approximately 1.4 percentage points over the baseline of 87.271±0.162%68% similarUnverifiedThe fine-tuned Qwen3.5-4B model improved accuracy on BU Bench V1 from 15% to 53%.68% similarUnverifiedOn an internal benchmark of 2,843 multilingual customer service tickets, THX-01 achieved 98.4% accuracy, an ECE of 0.003, and a measured latency of approximately 10ms, outperforming TypeSafe Jev 1.13 (97.4% accuracy, ECE 0.007, latency 331ms).68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016988API
curl https://kongchang.com/api/v1/knowledge/claims/1016988MCP
get_claim(id=1016988)