AI-Assisted Engineering Should Track the Epistemic Status and Temporal Validity of Architectural Decisions

TL;DR

The paper argues that AI-assisted software engineering must track epistemic status and temporal validity of architectural decisions. It introduces the First Principles Framework (FPF), combining explicit epistemic layers, conservative WLNK-based aggregation via the Gödel t-norm, and automated evidence decay to surface stale assumptions, backed by a retrospective deployment audit showing substantial evidence decay. The framework includes the F-G-R trust tuple, the Gamma invariant quintet, the ADI reasoning cycle, and the Design Rationale Record, providing a structured, auditable approach to decision making under uncertainty. Pragmatic deployment evidence and research directions underscore the need for temporal accountability to prevent trust inflation and architectural erosion in production systems.

Abstract

This position paper argues that AI-assisted software engineering requires explicit mechanisms for tracking the epistemic status and temporal validity of architectural decisions. LLM coding assistants generate decisions faster than teams can validate them, yet no widely-adopted framework distinguishes conjecture from verified knowledge, prevents trust inflation through conservative aggregation, or detects when evidence expires. We propose three requirements for responsible AI-assisted engineering: (1) epistemic layers that separate unverified hypotheses from empirically validated claims, (2) conservative assurance aggregation grounded in the Gödel t-norm that prevents weak evidence from inflating confidence, and (3) automated evidence decay tracking that surfaces stale assumptions before they cause failures. We formalize these requirements as the First Principles Framework (FPF), ground its aggregation semantics in fuzzy logic, and define a quintet of invariants that any valid aggregation operator must satisfy. Our retrospective audit applying FPF criteria to two internal projects found that 20-25% of architectural decisions had stale evidence within two months, validating the need for temporal accountability. We outline research directions including learnable aggregation operators, federated evidence sharing, and SMT-based claim validation.

Figures (6)

• Figure 1: The F-G-R trust tuple. Each knowledge claim in FPF carries three dimensions: Formality (F) determines the rigor of expression, Scope (G) constrains evidence portability via congruence-level penalties, and Reliability (R) is the computed effective trust score $R_{\mathrm{eff}}$. F caps the maximum achievable R; G penalizes cross-context transfer.
• Figure 2: WLNK dependency graph (worked example). Green nodes have strong evidence; the red node (E2, F1-level blog evidence) caps the entire decision at $R_{\mathrm{eff}} = 0.70$. Upgrading E2 to an F2 load test would raise $R_{\mathrm{eff}}$ to $\min(0.95, 0.90) = 0.90$. Averaging would yield 0.85, masking the weak foundation.
• Figure 3: The ADI reasoning cycle. Abduction generates conjectures (L0), Deduction verifies logical consistency (L1), and Induction validates empirically (L2). Finalized decisions become Design Rationale Records (DRRs). Evidence decay or new anomalies trigger re-entry into the cycle.
• Figure 4: Evidence decay lifecycle for a single decision. A Redis session storage decision is created in July 2025 with $R_{\mathrm{eff}} = 0.90$. As the benchmark evidence approaches its validity window, the system transitions from green to amber. Upon expiration in January 2026, a STALE alert triggers one of three resolution paths: re-validate, waive with rationale, or deprecate.
• Figure 5: Staleness discovery modes (retrospective analysis of 62 ADRs). Of the 14 decisions with stale evidence, 12 were discovered reactively during incidents or refactoring; 2 remained dormant until our audit. With FPF decay tracking, all 14 would have triggered proactive alerts.

Theorems & Definitions (4)

• Theorem 1: Quintet Satisfaction
• proof
• Theorem 2: Idempotent Uniqueness
• proof