docs: rep4 bake-off write-up, MkDocs site, artifact-registry-backed experiments

docs/rep4-optimizer-results.md is the main deliverable: the model bake-off +
threshold re-tune experiment log, including the ROCm teardown deadlock root
cause and fix, DE concurrency tuning, the 16-combo results table, held-out
validation against 5 films never seen by the optimizer (macro F1 67.4% vs.
75.3% training — a real generalization gap), the frozen-bbox "ghost track"
failure mode found via annotated frame evidence, calibration curves per model,
and an isolated-effects breakdown of gallery scope vs. pose expansion.

MkDocs site (mkdocs.yml, docs/index.md) renders docs/*.md; scripts/docs/
pulls referenced images from the artifact registry and generates the
calibration chart at build time (see the tooling commit) rather than
committing images to the repo.

experiments/ now keeps only scripts + README + SESSION_STATE.md in git — every
data artifact (galleries, dumps, X-Ray corpus, montage frames, trajectories,
manifests, results) moved to the Gitea package registry. film-lut.template.json
is the committed placeholder for the gitignored file-lut.json (real local
movie paths, never shared — some source filenames carry scene-release tags).

Adds models/transnetv2.onnx (via Git LFS, matching the other ONNX models) for
the new scene-detection path.

README.md

@@ -46,10 +46,10 @@ Optional flags:
 ## Models
 
 The ONNX model weights live in `models/` (tracked via Git LFS):
-- `arcface_w600k_r50.onnx` — primary ArcFace embedder
-- `arcface_w600k_mbf.onnx`, `arcface_r18.onnx` — lighter alternatives
-- `LVFace-B_Glint360K.onnx` — LVFace embedder (ViT backbone, ICCV 2025), drop-in
-  ArcFace-compatible: same `[N,3,112,112]` input and 512-d output (see below)
+- `LVFace-B_Glint360K.onnx` — LVFace embedder (ViT backbone, ICCV 2025), the default
+  (best F1 in the rep4 model bake-off, see `docs/rep4-optimizer-results.md`)
+- `arcface_w600k_r50.onnx` — ArcFace embedder, previous default
+- `arcface_w600k_mbf.onnx`, `arcface_r18.onnx` — lighter ArcFace alternatives
 - `face_detection_yunet_2023mar.onnx` — YuNet face detector
 - `scrfd_500m_bnkps.onnx` — SCRFD face detector