Add AI disclosure layouts, tighten detection and provenance warnings

scripts/assets/visible-mark-candidates/README.md

@@ -23,7 +23,6 @@ from the provider's canonical name, the provider is named separately.
 | `samsung_en_alpha.png` | Samsung Galaxy AI label, English locale ("AI-generated content", bottom-left) | 5 corpus files | POS 0.11-0.30 vs NEG max 0.40 (binary); tophat/gray tried, no separation. The registered Italian engine scores 0.18-0.31 on the same files -- same layout class, wrong glyph template. |
 | `gemini_text_alpha.png` | "Generated with Gemini" text label (bottom-right; the registered gemini mark is the sparkle icon) | 3 corpus files | POS 0.07-0.22 vs NEG max 0.32; coverage gate finds the blob (0.29-0.35) but the Arial silhouette misses Google's letterforms. |
 | `notebooklm_alpha.png` | NotebookLM wordmark (bottom-right) | 12 corpus files | locate geometry not yet fitted; POS max 0.12. |
-| `dola_alpha.png` | DolaAI on images (the video mark is registered) | 12 corpus files | POS 0.11-0.21 vs NEG max 0.30. |
 | `mindvideo_alpha.png` | MindVideo.AI (top-right) | 11 corpus files | POS 0.29-0.32 vs NEG max 0.30 -- borderline overlap, not shippable. |
 | `higgsfield_alpha.png` | `HIGGSFIELD AI` wordmark (Higgsfield AI, bottom-right; the boxed `AI` variant shares the cohort) | 5 wordmark files (16 in the boxed-AI OCR cluster) | POS max 0.26 vs NEG max 0.22 -- no separation; the mark may be two-part (wordmark + boxed AI) and needs a composed template. |
 | `jianying_alpha.png` | `剪映AI` wordmark (Jianying / 剪映, the China product in the CapCut family; bottom-right) | 2 corpus files | POS 0.29 vs NEG max 0.35. |

scripts/render_overlay_variants.py

@@ -0,0 +1,68 @@
+"""Rebuild synthetic silhouettes for additional AI disclosure layouts."""
+
+from __future__ import annotations
+
+import logging
+import sys
+from pathlib import Path
+
+import cv2
+import numpy as np
+from PIL import Image
+
+ROOT = Path(__file__).resolve().parents[1]
+sys.path.insert(0, str(ROOT))
+from scripts.render_vendor_silhouettes import render  # noqa: E402
+
+log = logging.getLogger(__name__)
+ASSETS = ROOT / "src" / "remove_ai_watermarks" / "assets"
+CJK = {"font": "/System/Library/Fonts/Hiragino Sans GB.ttc", "font_index": 2}
+
+
+def centered_lines(
+    top: str, bottom: str, *, top_scale: float, bottom_height: float = 1.0, shear: float = 0.0
+) -> np.ndarray:
+    upper, lower = render(top, opts=CJK), render(bottom, opts=CJK)
+    if bottom_height != 1.0:
+        lower = cv2.resize(lower, (upper.shape[1], round(upper.shape[0] * bottom_height)))
+    else:
+        upper = cv2.resize(upper, (round(lower.shape[1] * top_scale), round(lower.shape[0] * 0.95)))
+    lines = [upper, lower]
+    result = np.zeros((sum(line.shape[0] for line in lines) + 2, max(line.shape[1] for line in lines)), np.uint8)
+    y = 0
+    for line in lines:
+        x = (result.shape[1] - line.shape[1]) // 2
+        result[y : y + line.shape[0], x : x + line.shape[1]] = line
+        y += line.shape[0] + 2
+    if shear:
+        h, w = result.shape
+        extra = round(abs(shear) * h)
+        result = cv2.warpAffine(result, np.float32([[1, shear, extra], [0, 1, 0]]), (w + extra, h))
+    return result
+
+
+def silhouettes() -> dict[str, np.ndarray]:
+    return {
+        "workbuddy_alpha.png": centered_lines("AI生成", "WORKBUDDY>_", top_scale=1.0, bottom_height=0.45),
+        "yuanbao_compact_alpha.png": centered_lines("元宝", "AI生成", top_scale=0.65, shear=-0.15),
+        "yuanbao_compact_gray_alpha.png": centered_lines("元宝", "AI生成", top_scale=0.65, shear=-0.15),
+        "doubao_outline_alpha.png": render("豆包AI生成", opts=CJK),
+        "samsung_ko_alpha.png": render(
+            "AI로 생성한 콘텐츠", opts={"font": "/System/Library/Fonts/AppleSDGothicNeo.ttc"}
+        ),
+        "microsoft_text_alpha.png": render(
+            "Made with AI", opts={"font": "/System/Library/Fonts/Supplemental/Arial.ttf"}
+        ),
+        "jimeng_label_alpha.png": render("AI生成", opts={"font": "/System/Library/Fonts/STHeiti Medium.ttc"}),
+    }
+
+
+def main() -> None:
+    logging.basicConfig(level=logging.INFO)
+    for name, alpha in silhouettes().items():
+        Image.fromarray(alpha).save(ASSETS / name)
+        log.info("Rendered %s, %s x %s", name, alpha.shape[1], alpha.shape[0])
+
+
+if __name__ == "__main__":
+    main()

scripts/render_vendor_silhouettes.py

@@ -73,7 +73,7 @@ MARKS = {
     "gemini_text_alpha.png": "Generated with Gemini",
     # Candidate wordmarks measured on a local evaluation corpus (unregistered).
     "notebooklm_alpha.png": "NotebookLM",
-    "dola_alpha.png": "DolaAI",
+    "dola_alpha.png": "Dola AI",
     "mindvideo_alpha.png": "MindVideo.AI",
     "higgsfield_alpha.png": "HIGGSFIELD AI",
     "capcut_alpha.png": "CapCut AI",
@@ -92,6 +92,7 @@ _REGISTERED = {f"{key}_alpha.png" for key in mark_keys()} & MARKS.keys()
 
 # Per-mark post-processing for the multi-line / slanted stamps (see render()).
 MARK_OPTS: dict[str, dict[str, Any]] = {
+    "dola_alpha.png": {"font": "/System/Library/Fonts/Supplemental/Arial Bold.ttf"},
     # Hiragino Sans GB W6, tight leading, dilation, and negative shear match the
     # standard Yuanbao stamp without clipping the lower line.
     "yuanbao_alpha.png": {