Risk-Limiting Operating-Point Authorization for Deepfake Video Detectors under Benchmark Shift: v6.7 Consolidated Reproducibility Package

Consolidated aggregate results and reproducibility code for the manuscript “Risk-Limiting Operating-Point Authorization for Deepfake Video Detectors under Benchmark Shift: Identity-Isolated Certification and Modern-Model Stress Testing.” Version 6.7 combines the registered original authorization study, the multi-architecture extension, the explicitly post-result HiDF and robustness analyses, and the pre-outcome-frozen FakeSTormer stress test in one navigable archive. A result-to-artifact map links manuscript claims to shareable tables, code, hashes, protocols and independent audits. Version 6.7 adds no new detector inference or scientific outcome; it consolidates the public evidence chain and improves reproducibility navigation. The package excludes source media, credentials, private paths, identities, crops, row-level labels, per-item predictions and third-party weights. Documentation and aggregate artifacts are CC BY-NC 4.0; project-authored Python and PowerShell code is MIT. Provider access conditions and upstream licences continue to govern restricted datasets, third-party code and detector weights.