arXiv：cs.AI· Harish Kant Pathak·· 3 小时前
TRACE：面向生产 AI 系统的可解释性债务治理框架
TRACE: A Governance Framework for Measuring Explainability Debt in Production AI Systems
AI 导读
TRACE 是一套包含七个工具的生产 AI 系统可解释性债务治理框架，其核心 Explainability Debt Score（EDS）量化低于治理阈值决策的占比。
正文
Abstract:Production AI systems deployed in high-stakes domains accumulate a governance liability that existing monitoring frameworks fail to detect: the progressive inability to explain individual decisions when regulators, auditors, or affected individuals demand accountability. We introduce TRACE (Transparency, Risk, Accountability, Compliance, and Explainability), a seven-instrument governance framework for measuring, tracking, and remediating Explainability Debt in production AI systems. The foundational instrument, the Explainability Debt Score (EDS), quantifies the proportion of production decisions falling below a governance-defined explainability confidence threshold at any point in time. Complementary instruments include DART (Debt Accumulation Rate Tracker for breach forecasting), SHIV (Scenario Health and Integrity Validator for daily governance), FDE (Feature Drift Evaluator for causal attribution), HVE (Human Validation Engine), AIDE (Audit Intervention Decision Engine), and ZERO (Zero Explainability Risk Optimiser for remediation). Through a twelve-month longitudinal case study of a production fraud detection system processing 50,000 daily financial transactions, achieving 98.46% accuracy and ROC-AUC of 0.9990, we demonstrate that an EDS of 0.23 on audit day was statistically predictable six months in advance using DART trajectory analysis (beta = 0.008/week, R-squared = 0.94, 95% CI: [0.006, 0.010]), and that 78% of Explainability Debt was concentrated in the highest-regulatory-risk decision category (transactions above $10,000), a risk asymmetry completely invisible to system-level metrics. TRACE provides the first quantitative operational architecture for EU AI Act Article 13 compliance in production AI deployment, establishing a new subdiscipline of explanation governance distinct from explanation generation.
| Comments: | 28 pages, 4 figures, 4 tables. Keynote presented at ICIDS 2026 (Manipal University Jaipur) and IEEE Al-Khwarizmi 2026. IEEE Senior Member #101994709. U.S. Provisional Patent Application No. 64/159,545 (USPTO Confirmation #9430) covers aspects of the TRACE/EDS framework |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.10957 [cs.LG] |
| (or arXiv:2610.10957v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10957 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Harish Pathak [view email]
[v1]
Wed, 7 Oct 2026 22:19:36 UTC (515 KB)
来源：arXiv：cs.AI · arxiv.org