Decision Trace Schema for Governance Evidence in Real-Time Risk Systems
2026-04-10 • Computers and Society
Computers and Society
AI summaryⓘ
The authors identify that current logging methods for automated decisions are incomplete because they don’t capture all parts needed to understand how decisions are made, calling this the Fragmented Trace Problem. They created the Decision Event Schema (DES), a JSON-based format that combines data from four key layers involved in decision-making, like machine learning and policy checks, into one record. DES allows different levels of detail depending on how risky or frequent the decisions are and is designed to work with high-speed systems. Their evaluation shows DES covers all relevant layers better than existing formats, helping both system builders and regulators track decision processes more clearly.
Automated decision systemsLogging formatFragmented Trace ProblemDecision Event SchemaJSON SchemaMachine learning inferenceRule evaluationGovernance metadataEvidence tiersHigh-throughput systems
Authors
Oleg Solozobov
Abstract
Automated decision systems produce operational data across multiple infrastructure layers, yet no single logging format captures the complete governance-relevant record of how a decision was reached. Regulatory frameworks prescribe what must be recorded without specifying a data model for how to record it -- a gap this paper terms the Fragmented Trace Problem. Following a design science methodology, the paper presents the Decision Event Schema (DES), a JSON Schema specification that bridges four infrastructure layers -- ML inference, rule/policy evaluation, cross-system coupling, and governance metadata -- within a single per-decision event structure. The schema employs degradation-aware field design: each of six top-level field groups maps to a governance evidence property and the degradation type it must resist. DES defines ten required root-level fields and introduces a tiered evidence strategy (lightweight, sampled, full) that enables organizations to match evidence completeness to decision risk and throughput. A mechanism feasibility analysis demonstrates compatibility with the highest-throughput integrity mechanisms at production-scale decision rates. Evaluation against 25+ existing formats confirms that DES is the only specification covering all four layers simultaneously. The schema offers practitioners a reference adoptable directly or adaptable through namespace extensions, and regulators a mapping from requirements to minimum evidence tiers.