Rename '(Corp)' variant to '(Composite)' to match the paper

The locality-preserving post-processing variant is referred to as
"ViTeX-14B (Composite)" in the paper and on the leaderboard. Update the
model card and the make_corp_baseline.py docstring to match. The
script filename and the default output directory (ViTeX-14B_Corp/) are
left as legacy identifiers so existing eval pipelines keep working.

README.md

@@ -35,7 +35,7 @@ This repository is fully self-contained — it bundles the trained weights, the
 ├── README.md
 ├── requirements.txt
 ├── inference_example.py            run ViTeX-14B on one (video, mask, glyph) tuple
-├── make_corp_baseline.py           build the ViTeX-14B (Corp) variant from raw predictions
+├── make_corp_baseline.py           build the ViTeX-14B (Composite) variant from raw predictions
 ├── vitex_14b.safetensors           (8 GB — trained adapter weights)
 ├── diffsynth/                      (bundled inference library)
 └── base_model/                     (70 GB — frozen base model files)
@@ -80,7 +80,7 @@ python inference_example.py \
 
 The script automatically uses the bundled `base_model/` and `vitex_14b.safetensors` — no extra downloads.
 
-## Locality-preserving variant: ViTeX-14B (Corp)
+## Locality-preserving variant: ViTeX-14B (Composite)
 
 `make_corp_baseline.py` is a deterministic, training-free post-processing wrapper that composes ViTeX-14B's predicted text region back onto the source video. Two per-frame operations:
 

make_corp_baseline.py

@@ -1,4 +1,4 @@
-"""Build the ViTeX-14B (Corp) baseline.
+"""Build the ViTeX-14B (Composite) baseline.
 
 For each test clip:
   1. Read source video, ViTeX-14B prediction, and the dilated text mask.