Verifier-Faithful Cross-Layer In-Kernel Machine Learning for Multi-Stage Intrusion Detection: generated results data

Generated results data supporting the article Verifier-Faithful Cross-Layer In-Kernel Machine Learning for Multi-Stage Intrusion Detection. Contains the canonical aggregator output over twelve network x host corpus pairs, the raw per-trial outputs behind every figure and table, the content-hashed calibration, and the recorded execution environment. The live in-kernel measurements are included: the asynchronous-state faithfulness window with its in-kernel maturity-sweep replay, BPF-LSM fidelity and enforcement runs, static verifier cost and classification latency, the live cross-layer capture, and the four-stage kill-chain testbed whose per-stage fused verdicts are plotted in the article. Every results file declares STATUS: validated and the SHA-256 of its calibration. Confidence intervals are 5000-resample percentile bootstrap over at least 30 seeds per configuration; pairwise comparisons carry Holm step-down correction. The composed cross-layer corpus is semi-synthetic and disclosed as such in the article. Source code is not part of this deposit. Raw third-party corpora are not redistributed; each is obtainable from the original host cited in the article's Data availability statement.