Immutable reproducible artifact for Sharp Target-Domain Certificates for Quantum-Kernel Advantage under Distribution Shift. Version 1.1.4 contains a sharp finite-target identified interval for the predictive advantage of one fixed model over the best member of a prespecified classical-kernel reference family for any additive bounded loss on a finite label space. It proves endpoint attainment, monotone contraction under partial target-label audits, and information optimality; zero-one accuracy admits closed-form zero-label and partial-label certificates. The empirical artifact preserves the complete controlled quantum-kernel benchmark: train-only regularization, target-label-free deployment selection, matched search budgets, factorial and shortcut analyses, external TableShift corroboration, separable-product versus entangling-ZZ strata, circuit resources, geometry diagnostics, repeated finite-shot perturbations, the frozen 30/60/115 reference-breadth frontier, and the retrospective eight-shift certificate audit. Prospective corroboration in two technically eligible tasks met the predefined Gate-2 criteria against the prespecified classical-kernel reference family; a third task failed its prespecified feature gate before model execution. The artifact does not claim universal classical superiority, classical simulability, hardware advantage, quantum speedup, or population-wide ordering. This study falls outside the scope of institutional ethics review because it consists exclusively of secondary analyses of publicly available, deidentified datasets, without recruitment, interaction, intervention, access to direct identifiers, or any attempt at reidentification. Ethics approval and additional informed consent were not required. No ethics approval or exemption is claimed. The archive contains source code, frozen specifications, prediction locks, physically separated label archives, complete machine-readable outputs, tests, manuscript sources, final PDFs, and SHA-256 checksums. Raw benchmark source records are not redistributed.