🤖 AI Summary
This work addresses the limitations of traditional Euclidean-space anomaly detection in distinguishing between safety trade-offs and risk accumulation, as well as its inability to adapt to continuously evolving system architectures. Drawing on Rasmussen’s dynamic safety model, the authors propose a drift observability framework in the simplex space, introducing Aitchison geometry and isometric log-ratio coordinates to software system monitoring for the first time. This approach enables coordinate-invariant modeling of compositional operational signals, precisely characterizing drift direction and distance to safety boundaries. By integrating phylogeny-aware aggregation with engineering artifact–driven boundary definitions, the study establishes a continuously comparable mechanism tailored to architectural evolution, facilitating interpretable early warnings and falsifiable hypotheses. The framework thus provides both theoretical foundations and practical pathways for drift observability in complex software systems.
📝 Abstract
Monitoring drift into failure is hindered by Euclidean anomaly detection that can conflate safe operational trade-offs with risk accumulation in signals expressed as shares, and by architectural churn that makes fixed schemas (and learned models) stale before rare boundary events occur. Rasmussen's dynamic safety model motivates drift under competing pressures, but operationalizing it for software is difficult because many high-value operational signals (effort, remaining margin, incident impact) are compositional and their parts evolve. We propose a vision for drift observability on the simplex: model drift and boundary proximity in Aitchison geometry to obtain coordinate-invariant direction and distance-to-safety in interpretable balance coordinates. To remain comparable under churn, a monitor would continuously refresh its part inventory and policy-defined boundaries from engineering artifacts and apply lineage-aware aggregation. We outline early-warning diagnostics and falsifiable hypotheses for future evaluation.