Unverified50% confidenceBenchmarkExact time
Tether's benchmark tests show a risky-call interception rate of 6/6 (100%), a legitimate-task false-block rate of 0/10 (0%), and 10/10 legitimate tasks uninterrupted after revocation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/18/2026
First Seen
Valid until: 1/16/2027
Sources
Related Entities
Related Claims
UnverifiedIn a benchmark of 30 held-out test windows, TabPFN achieved 100.0% overall accuracy, 100.0% shock recall, 0.33 ms CPU latency, 0.0% step-frequency false alarms, and required no training or tuning.67% similarUnverifiedThe SAFETY parameter (default 0.80) is a hard multiplier, not a suggested value, forcing the plan to absorb a 20% estimation error without touching the last fifth of the quota.66% similarUnverifiedIn a controlled experiment in which dangerous commands were mixed in, humans intercepted only 13.6% of the dangerous operations, while the machine classifier intercepted 89%.66% similarUnverifiedIn the τ-bench retail environment benchmark test (30 test tasks, simulated customers, single run, solvi 0.8.0, gpt-oss-120b as the Agent), without the guard 18 tasks were solved and the environment rejected 10 mutating calls; with the guard 14 tasks were solved and the environment rejected 0 mutating calls.66% similarUnverifiedIn the ablation experiment, replacing the gate with the naïve check commonly used in unconstrained systems (fewer visible errors in recent trajectories), the same loop admitted 309 harmful changes and left the miss rate above 10% in 49 out of 90 runs.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1062006API
curl https://kongchang.com/api/v1/knowledge/claims/1062006MCP
get_claim(id=1062006)