Unverified50% confidenceBenchmarkExact time
In the hybrid mode at τ=0.4, 27 of the 400 cases are escalated (6.8%), billed Tokens drop from 1,222,211 to 82,499, and the saving including plugin overhead is 86.1%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027
Sources
Related Entities
Related Claims
UnverifiedThe published 4.22% additional cost comes from the Tau-bench test, in which the guardrail intervened only once out of 11,355 actions.66% similarUnverifiedAt τ=0.6 the confidence distribution is concentrated around a median of 0.6294, and 851 of the 2000 decisions (42.6%) fall below 0.6, which by case count is 90.8%.65% similarUnverifiedOn the hard tier, recall@5 improved from 0.000 to 0.955 (under default blending weights), and reached 1.000 when using the lower-bound variant.64% similarUnverifiedIn an S&P 500 option chain experiment, after sparsifying the data to retain only 20 quotes and introducing no-arbitrage constraints, the out-of-sample extrapolation error on the held-out set decreased by 22% and the calendar arbitrage occurrence rate dropped from 10% to 1%.63% similarUnverifiedIn the specific experimental case, the overlapping-anchor scheme (n=912) showed the model at 55.2% versus the majority class at 51.1%, a net advantage of +4.1pp, about 2.4 standard errors; the non-overlapping-anchor scheme (n=163) showed 59.5% versus 54.0%, a net advantage of +5.5pp, about 1.4 standard errors.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1017004API
curl https://kongchang.com/api/v1/knowledge/claims/1017004MCP
get_claim(id=1017004)