Add CUA-S1-FORMS FP16 Core ML conversion and verified artifacts
Add the 706,048-parameter CUA-S1-FORMS decision scorer as a portable FP16 Core ML package and compiled FluidAudio bundle, with encoding helper, pinned provenance, licenses, checksums, and conversion reports.
Validation uses the complete pinned 196-row upstream demo, not a new synthetic dataset. PyTorch, Core ML ALL, and Core ML CPU_AND_NE select all 196 labeled options correctly. Maximum probability differences are 0.003099 and 0.002336 respectively, below the preselected 0.005 tolerance. The unmodified Cua evaluator reports zero wrong actions, wrong targets, or unsafe actions on these saved predictions. Eighteen Python regression tests pass.
FluidAudio's Swift runtime independently matches all 196 decisions against the PyTorch probabilities (maximum error 0.002336), including local package loading, shared compiled-model cache loading, UTF-8 encoding, and concurrent/reordered-option checks. The Swift library builds; local XCTest execution is unavailable because this Mac has Command Line Tools without the XCTest framework.
The package is 1,511,163 bytes. Timings and ANE/CPU placement are exploratory measurements on the documented M5 Pro, not general GUI-automation or mobile-device benchmarks. The caller supplies document entities and UI descriptions and owns action validation and execution.
Related code PRs:
- https://github.com/FluidInference/mobius/pull/97
- https://github.com/FluidInference/FluidAudio/pull/936
Merge this model PR before enabling FluidAudio's default download path. This PR does not merge or release the model automatically.
All 18 distributed files were downloaded from commit c87b915d302bdbff644709408d8fbd8c8effe894 and verified against the staged SHA-256 manifest. The downloaded artifacts also passed the same Swift checks.