We present SCI, a closed-loop, control-theoretic framework that models interpretability as a regulated state. SCI formalizes the interpretive error Delta SP and actively drives SP(t) in [0, 1] ("Surgical Precision") toward a target via a projected update on the parameters Theta under a human-gain budget. The framework operates through three coordinated components: (1) reliability-weighted, multiscale features P(t, s); (2) a knowledge-guided interpreter psi_Theta that emits traceable markers and rationales; and (3) a Lyapunov-guided controller equipped with rollback, trust-region safeguards, and a descent condition. Across biomedical (EEG/ECG/ICU), industrial (bearings/tool wear), and environmental (climate/seismic) domains, SCI reduces interpretive error by 25-42% (mean 38%, 95% confidence interval 22-43%) relative to static explainers while maintaining AUC/F1 within approximately 1-2 percentage points of baseline. SCI also reduces SP variance from 0.030 to 0.011, indicating substantially more stable explanations. Modeling interpretability as a control objective yields steadier, faster-recovering, and more trustworthy interpretive behavior across diverse signal regimes.

翻译：本文提出SCI，一种基于闭环控制理论的框架，将可解释性建模为受调控的状态。SCI形式化定义了可解释性误差ΔSP，并在人类增益预算约束下，通过参数Θ的投影更新，主动驱动SP(t)（“手术精度”）在[0, 1]区间内趋近目标值。该框架通过三个协同组件运行：(1) 可靠性加权的多尺度特征P(t, s)；(2) 知识引导的解释器ψ_Θ，可生成可追踪的标记与归因依据；(3) 具备回滚机制、信赖域保护及下降条件的李雅普诺夫引导控制器。在生物医学（脑电图/心电图/重症监护）、工业（轴承/刀具磨损）及环境（气候/地震）领域实验中，相较于静态解释器，SCI将可解释性误差降低25-42%（均值38%，95%置信区间22-43%），同时保持AUC/F1分数与基线相差约1-2个百分点。SCI还将SP方差从0.030降至0.011，表明其解释稳定性显著提升。通过将可解释性建模为控制目标，该框架能在多样化的信号场景中实现更平稳、更快恢复且更可信的解释行为。