TRACE: A Governance Framework for Measuring Explainability Debt in Production AI Systems

Key points

• 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.1
• 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.1
• 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).1
• 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.1

Sources (1)

• [1]TRACE: A Governance Framework for Measuring Explainability Debt in Production AI Systems
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 10:19 PM

  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.

  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.

Extractive summary: sentences quoted from the sources.