Coverage and Structural Relations of Three Agentic AI Risk Taxonomies Across 131 Documented Incidents — Supplementary Dataset, Codebook, and Analysis Scripts

Supplementary materials for the manuscript "Coverage and Structural Relations ofThree Agentic AI Risk Taxonomies Across 131 Documented Incidents" (submitted toDiscover Artificial Intelligence). Version 2, accompanying the second revision. The deposit contains 131 agent-related AI incidents drawn from the AI IncidentDatabase (2014-2026), each coded against the OWASP Top 10 for Agentic Applications2026, the Microsoft AI Red Team taxonomy of agentic failure modes, and the NIST AIRisk Management Framework. Files: the coded workbook (XLSX and CSV); a codebookdocumenting category boundary decisions; the reconciliation log; an independentblinded coding pass over all 131 incidents in two conditions, with both coders'per-incident output and rationales; sensitivity analyses for the pre-2022 subset,the keyword threshold and the failure-only subsample; a redacted copy of the May2026 scoping document with the deviations from it tabulated; twelve Python scriptsreproducing every reported statistic and all seven figures; and the figures atpublication resolution. Incident source URLs and access dates are included forevery record. Incident data derives from the AI Incident Database(incidentdatabase.ai), licensed CC BY 4.0.