diff --git a/.github/workflows/distribute.yml b/.github/workflows/distribute.yml
index 430def4..d9125db 100644
--- a/.github/workflows/distribute.yml
+++ b/.github/workflows/distribute.yml
@@ -4,7 +4,7 @@ name: Distribute on release
 # PyPI is handled by publish.yml. This workflow event-drives the three channels
 # that would otherwise be manual:
 #   - Homebrew tap: rewrite the formula's url + sha256 to the new sdist.
-#   - HF Space: factory-rebuild so it reinstalls the latest sdist from PyPI.
+#   - HF Space: factory-rebuild the version already pinned in the Space repo.
 #   - ComfyUI: sync, test, and publish the node against the exact library release.
 # All wait for the freshly published sdist to appear on PyPI first, since the
 # Release event fires in parallel with publish.yml's upload.
diff --git a/README.md b/README.md
index 2c87b15..509b7e6 100644
--- a/README.md
+++ b/README.md
@@ -7,13 +7,14 @@ Remove AI provenance marks from images and video you generated yourself:
 - C2PA, EXIF, XMP, IPTC, and related AI metadata.
 
 Video support covers provenance identification, complete visible-plus-metadata
-cleaning, directory batches, visible Sora, Veo, Seedance, Dola, Hailuo, and
-Kling mark removal, and oracle-certified VAE regeneration for video SynthID
+cleaning, directory batches, visible Sora, Veo, Seedance, Dola, Hailuo AI, and
+Kling AI mark removal, and oracle-certified VAE regeneration for video SynthID
 removal.
 
 > [raiw.cc](https://raiw.cc) runs this library as a hosted service, with the GPU
-> included and nothing to install. Visible mark and metadata removal are free
-> there; invisible watermark removal is paid.
+> included and nothing to install. Visible mark and metadata removal at Standard
+> output up to 12 MP are free there; original resolution above 12 MP and invisible
+> watermark removal are paid.
 
 [![PyPI](https://img.shields.io/pypi/v/remove-ai-watermarks?logo=pypi&logoColor=white)](https://pypi.org/project/remove-ai-watermarks/)
 [![Python](https://img.shields.io/pypi/pyversions/remove-ai-watermarks?logo=python&logoColor=white)](https://pypi.org/project/remove-ai-watermarks/)
@@ -230,6 +231,13 @@ features, and development setup.
 | --- | --- |
 | ![Image with a visible Gemini watermark](demo_banana_before.png) | ![Image after visible watermark removal](demo_banana_after.png) |
 
+The `after` raster is generated from the tracked `before` raster by the public path:
+
+```bash
+uv run remove-ai-watermarks visible demo_banana_before.png \
+  --backend cv2 -o demo_banana_after.png
+```
+
 ### High quality invisible removal
 
 `qwen-zimage` is the default profile: a Qwen-Image-2512 Lightning pass under Canny
@@ -311,8 +319,8 @@ remove-ai-watermarks batch ./images --mode all
 
 Visible mark support includes:
 
-- Google Gemini and Nano Banana sparkle;
-- Doubao, Jimeng, Qwen, Kling, Yuanbao, Baidu, LibLibAI, and RunningHub labels;
+- Google Gemini and Nano Banana visible sparkle watermark;
+- Doubao, Jimeng, Qwen, Kling AI, Yuanbao, Baidu, LiblibAI, and RunningHub labels;
 - one calibrated Samsung Galaxy AI label variant.
 
 Metadata and provenance inspection covers C2PA, EXIF, XMP, IPTC, common
diff --git a/data/README.md b/data/README.md
index a76aadd..4160f67 100644
--- a/data/README.md
+++ b/data/README.md
@@ -48,16 +48,17 @@ runtime assets.
 video removal profile works, so it is also the source of truth for three shipped
 defaults: `tests/test_video_invisible.py` asserts that `noise_std`, `long_side`,
 and `fps` together match a row this manifest records as certified. Changing one
-of those three without adding the row that certifies it fails the suite. `vae` is
-deliberately outside that check because neither tracked row records one; add it
-to the assertion in the same commit as the first row that does.
+of those three without adding the row that certifies it fails the suite. Both
+historical rows mark `vae` as `unrecorded`: the repository must not infer a model
+identity from the current default. Add it to the assertion in the same commit as
+the first oracle row that records and verifies one.
 
 | Column | Meaning |
 | --- | --- |
 | `date`, `source_url`, `source_sha256` | Identify the carrier. |
 | `source_width`, `source_height`, `source_fps` | Carrier geometry. Without it the actual downscale factor of a row cannot be recovered later. |
 | `duration_seconds`, `source_verdict` | Clip length submitted and the verifier's reading of the untouched carrier. |
-| `vae`, `noise_std`, `long_side`, `fps`, `seed` | The full run configuration. |
+| `vae`, `noise_std`, `long_side`, `fps`, `seed` | The run configuration. `unrecorded` means the historical run did not preserve the VAE identity. |
 | `output_sha256` | Identifies the exact submitted file. |
 | `output_verdict` | One of `detected`, `not_detected`, `indeterminate`, `refused`. |
 | `output_verdict_text` | The verifier's wording, verbatim. |
diff --git a/data/contentseal/README.md b/data/contentseal/README.md
index c6ed21b..3797fb5 100644
--- a/data/contentseal/README.md
+++ b/data/contentseal/README.md
@@ -16,9 +16,12 @@ plus hash and is not stored.
   embedded in the watermark payload. Both survived a 512 px LANCZOS resize and
   a full-size JPEG q85 re-encode (same ID returned), so the payload is more
   robust than the detection threshold.
-- Center crops lose the seal: 50% and 33% linear center crops of two different
-  images all returned "No AI signatures from Meta were found", consistent with
-  the Reuters 2026-07-11 analysis (55% missed after cropping).
+- Three checked center crops lost the seal: 50% and 33% linear crops of the fox
+  and the 50% crop of the text poster returned "No AI signatures from Meta were
+  found". The text poster's 33% crop was not checked because the daily oracle
+  limit was reached, so its empty verdict is not evidence either way. The checked
+  results are consistent with the Reuters 2026-07-11 analysis (55% missed after
+  cropping).
 - API outputs carry XMP `iptcExt:DigitalSourceType =
   trainedAlgorithmicMedia`, so local `identify` flags them via the existing
   Made-with-AI path. Metadata-stripping transforms fall back to unknown, and
@@ -62,8 +65,8 @@ the calibration rows below is the race-free variant.
 
 The library resolves strength per vendor with measured floors (OpenAI
 0.07675 / Google 0.27 / Microsoft InvisMark 0.15 in
-`_internal/watermark_profiles.py`). Meta Content Seal has no floor yet; the
-goal of these rows is to measure one by that same methodology: independent
+`_internal/watermark_profiles.py`). Meta Content Seal had no floor before this
+calibration; these rows measure one by the same methodology: independent
 generations, each one's first-clean boundary, floor = worst boundary plus the
 observed cross-source spread.
 
@@ -83,7 +86,16 @@ Measured (2026-08-26/27, oracle `meta.ai/identification`):
   names it explicitly on stripped files (implying the scrub runs).
 ## Regeneration
 
-API key is not stored in this repository. Regenerate with the script pattern
-from the session (env `MUSE_API_KEY`, endpoint
-`https://api.meta.ai/v1/images/generations`, model `muse-image-1.0`); prompts
-are recorded per file in `manifest.csv`.
+The eight deterministic crop, resize, and JPEG variants can be reproduced and
+hash-checked from the tracked originals:
+
+```bash
+uv run python scripts/contentseal_transforms.py /tmp/contentseal-derived
+```
+
+The Meta API generations and remote GPU outputs are not reproducible from this
+repository alone. Their prompts, exact output hashes, model/profile settings,
+and oracle results are recorded in `manifest.csv`, but the generation API is
+stochastic and the private worker environment is not tracked. `MUSE_API_KEY` and
+the anonymous detector session are deliberately absent. A new calibration must
+therefore create new manifest rows rather than claiming to recreate these bytes.
diff --git a/data/evaluations/fidelity/anytext2-restoration-2026-08-13.csv b/data/evaluations/fidelity/anytext2-restoration-2026-08-13.csv
index 43df6e1..8eced92 100644
--- a/data/evaluations/fidelity/anytext2-restoration-2026-08-13.csv
+++ b/data/evaluations/fidelity/anytext2-restoration-2026-08-13.csv
@@ -1,4 +1,4 @@
 date,source_commit,fixture,variant,model,model_revision,model_sha256,ocr_route,text_cer,img_lpips,ssim,psnr_db,output_sha256,provider_oracle,notes
-2026-08-13,2d03a00,Gemini_Generated_Image_633uuy633uuy633u.png,qwen-zimage,,,,"Paddle ch",0.074,0.289,0.696,23.3,4b05489c7a79f993d35d32528de792baad5a3e33ee950afa147caf5d3e0621,not_run,Exact Qwen baseline reused from text-restoration benchmark
+2026-08-13,2d03a00,Gemini_Generated_Image_633uuy633uuy633u.png,qwen-zimage,,,,"Paddle ch",0.074,0.289,0.696,23.3,4b05489c7a79f993d35d32528de792baad5a3e33ee950afa147caf5d3e0621a6,not_run,Exact Qwen baseline reused from text-restoration benchmark
 2026-08-13,2d03a00,Gemini_Generated_Image_633uuy633uuy633u.png,qwen-zimage-anytext2-default,AnyText2-SD1.5,b06c583a583818f3679665ef67b51363f107853c,7d5d593928d842500e0da101ab6a1ae28a8d21403441ca62c813c4f92529ace8,"Paddle ch",0.185,0.338,0.642,18.2,87729fe7e0482d2cead6d3b7c7dd386ecc75ab3d8658131c54e67528b8f9feeb,not_run,Fidelity gate failed; padded crop recognition CER 0.074 still shows two substituted characters; locally composited three-line edit; 20 DDIM steps; seed 0
 2026-08-13,2d03a00,Gemini_Generated_Image_633uuy633uuy633u.png,qwen-zimage-anytext2-mimic,AnyText2-SD1.5,b06c583a583818f3679665ef67b51363f107853c,7d5d593928d842500e0da101ab6a1ae28a8d21403441ca62c813c4f92529ace8,"Paddle ch",0.222,0.345,0.644,17.9,f5198d8f2365b79880aba8ea6b0c3885142b9de21c9f7f4f6712ac4a0db8dd85,not_run,Fidelity gate failed; source glyph masks supplied as font hints; 20 DDIM steps; seed 0
diff --git a/data/evaluations/video-synthid-oracle.csv b/data/evaluations/video-synthid-oracle.csv
index a740419..89dd3e4 100644
--- a/data/evaluations/video-synthid-oracle.csv
+++ b/data/evaluations/video-synthid-oracle.csv
@@ -1,3 +1,3 @@
 date,source_url,source_sha256,source_width,source_height,source_fps,duration_seconds,source_verdict,vae,noise_std,long_side,fps,seed,output_sha256,output_verdict,output_verdict_text,output_detected_range,track,session_id,stratum,psnr_db,temporal_residual_ratio
-2026-07-31,https://storage.googleapis.com/gdm-deepmind-com-prod-public/media/media/veo__veo-3__off-road.mp4,79a552b9406a079682440c31f14d33a10ba8e1b8b2e96425f5de70f63350299d,1920,1080,24,8,detected_all_frames,,0.10,512,12,0,079165105d4c56e1612091987c08c2627049423025f74c0d4e245fb47c2ff0e3,detected,,,,,,26.2932,1.0072
-2026-07-31,https://storage.googleapis.com/gdm-deepmind-com-prod-public/media/media/veo__veo-3__off-road.mp4,79a552b9406a079682440c31f14d33a10ba8e1b8b2e96425f5de70f63350299d,1920,1080,24,8,detected_all_frames,,0.15,512,12,0,1c4046bcfdead138353b4e2a73339ba227bb5e544878d80c5bc6cd8427c7b00e,not_detected,,,,,,25.3911,1.0578
+2026-07-31,https://storage.googleapis.com/gdm-deepmind-com-prod-public/media/media/veo__veo-3__off-road.mp4,79a552b9406a079682440c31f14d33a10ba8e1b8b2e96425f5de70f63350299d,1920,1080,24,8,detected_all_frames,unrecorded,0.10,512,12,0,079165105d4c56e1612091987c08c2627049423025f74c0d4e245fb47c2ff0e3,detected,,,,,,26.2932,1.0072
+2026-07-31,https://storage.googleapis.com/gdm-deepmind-com-prod-public/media/media/veo__veo-3__off-road.mp4,79a552b9406a079682440c31f14d33a10ba8e1b8b2e96425f5de70f63350299d,1920,1080,24,8,detected_all_frames,unrecorded,0.15,512,12,0,1c4046bcfdead138353b4e2a73339ba227bb5e544878d80c5bc6cd8427c7b00e,not_detected,,,,,,25.3911,1.0578
diff --git a/data/synthid/README.md b/data/synthid/README.md
index 55cf3b5..565a2ab 100644
--- a/data/synthid/README.md
+++ b/data/synthid/README.md
@@ -160,7 +160,7 @@ sparkle; the SynthID *pixel* itself has no local detector (oracle only).
 
 Key takeaways:
 - The same model differs by *surface*: Gemini app wraps C2PA, AI Studio (API/playground) emits none -- only the pixel + sparkle survive.
-- Microsoft Designer's DALL-E backend inherits OpenAI's C2PA+SynthID (issuer "OpenAI, Microsoft"); Bing now runs Microsoft's own **MAI-Image** and signs C2PA as "Microsoft" (not OpenAI/DALL-E).
+- Microsoft Designer's DALL·E backend inherits OpenAI's C2PA+SynthID (issuer "OpenAI, Microsoft"); Bing now runs Microsoft's own **MAI-Image** and signs C2PA as "Microsoft" (not OpenAI/DALL·E).
 - Meta uses the IPTC `digitalSourceType` marker, not C2PA or SynthID.
 - The open imwatermark fires only on *pristine* output from a pipeline that runs the encoder (diffusers default, official BFL) -- not from re-hosts (Krea, Stability hosted SDXL) or re-encoded design exports (Recraft, Canva). Ideogram's only signal is the EXIF `Make` tag.
 - Bing and Grok web UIs are uncooperative for autonomous capture (no document_idle for screenshots; blob downloads intermittently no-op; low-res in-chat previews). Use their native download button manually if a full-res sample is needed.
diff --git a/demo_banana_after.png b/demo_banana_after.png
index 771c3ec..0743a4b 100644
Binary files a/demo_banana_after.png and b/demo_banana_after.png differ
diff --git a/docs/cli.md b/docs/cli.md
index ed67bf9..37aec29 100644
--- a/docs/cli.md
+++ b/docs/cli.md
@@ -434,10 +434,10 @@ user can act on rather than after a model load.
 ### Restore operator-verified text
 
 `--text-manifest` enables the experimental `vae-glyphs` post-pass. It reconstructs
-the source with the Qwen VAE, blends 15% of that reconstruction into the normal
-`qwen-zimage` result, erases the annotated candidate glyphs with LaMa, and composites
-only the reconstructed glyph cores through source-derived silhouettes. It does not
-run OCR or choose which strings are correct.
+the source with the Qwen VAE, erases the annotated candidate glyphs with LaMa, and
+composites only the reconstructed glyph cores through source-derived silhouettes. It
+does not run OCR or choose which strings are correct. The optional `--fidelity-anchor`
+described below additionally blends 15% of the reconstruction across the full frame.
 
 Install the combined extra and run only with an operator-verified manifest:
 
diff --git a/docs/controlnet-removal-pipeline-research.md b/docs/controlnet-removal-pipeline-research.md
index f5f10ed..4b56600 100644
--- a/docs/controlnet-removal-pipeline-research.md
+++ b/docs/controlnet-removal-pipeline-research.md
@@ -641,7 +641,7 @@ photo only).
 
 **Sources.** https://arxiv.org/abs/2206.11253 (CodeFormer) · https://github.com/sczhou/CodeFormer ·
 https://arxiv.org/pdf/2401.07519 (InstantID) ·
-https://openaccess.thecvf.com/content/WACV2024/papers/Suin_Diffuse_and_Restore... (region-adaptive) ·
+https://openaccess.thecvf.com/content/WACV2024/html/Suin_Diffuse_and_Restore_A_Region-Adaptive_Diffusion_Model_for_Identity-Preserving_Blind_WACV_2024_paper.html (region-adaptive) ·
 https://arxiv.org/pdf/2504.12809 (saliency-aware watermark removal)
 
 ## Provenance
diff --git a/docs/development.md b/docs/development.md
index e102eba..378160f 100644
--- a/docs/development.md
+++ b/docs/development.md
@@ -1,5 +1,9 @@
 # Development
 
+Standalone evaluation, calibration, and release utilities are catalogued in
+[`scripts/README.md`](../scripts/README.md). They are maintainer tools rather than
+installed commands, and their local data inputs remain outside the repository.
+
 Read this reference for environment setup, dependency recovery, CI behavior, and fixture policy. The always-loaded invariants remain in [`.claude/rules/development.md`](../.claude/rules/development.md).
 
 ## Local environment
diff --git a/docs/installation.md b/docs/installation.md
index c249ef8..529d409 100644
--- a/docs/installation.md
+++ b/docs/installation.md
@@ -114,6 +114,7 @@ application actually uses:
 | `lama` | big-LaMa ONNX fill backend | `visible`, ONNX Runtime | Model download, no Torch |
 | `qwen-zimage` | Invisible image-watermark removal, both CUDA-only profiles | `diffusion`, DiffSynth | Yes |
 | `text-restoration` | Opt-in verified Qwen-VAE glyph restoration | `qwen-zimage`, `lama` | Yes |
+| `text-draft` | Draft OCR proposals for operator verification | PaddleOCR, PaddlePaddle | Model download, no Torch |
 | `all` | Every production feature available on the active Python | All compatible rows above | Yes |
 | `dev` | Tests, linting, typing, and upstream parity checks | `video`, `detect`, upstream invisible-watermark | Yes, for parity tests |
 
@@ -130,12 +131,15 @@ flowchart LR
     qwen["qwen-zimage"] --> diffusion
     text["text-restoration"] --> qwen
     text --> lama
+    draft["text-draft"]
     heif
     trustmark
 ```
 
-`heif` and `trustmark` are independent branches. Combine them explicitly with
-another feature when required. TrustMark requires NumPy 1.x, which has no
+`heif`, `trustmark`, and `text-draft` are independent branches. Combine them
+explicitly with another feature when required. `text-draft` is excluded from
+`all` because it proposes unverified OCR annotations and is not a production
+removal path. TrustMark requires NumPy 1.x, which has no
 CPython 3.13 or 3.14 wheels, so that branch is available only on Python
 3.11-3.12. The `all` bundle contains every production branch compatible with
 the active Python and never includes `dev`.
diff --git a/docs/known-limitations.md b/docs/known-limitations.md
index e572826..88a8153 100644
--- a/docs/known-limitations.md
+++ b/docs/known-limitations.md
@@ -416,7 +416,7 @@ remain identical because isolated decoder hits can otherwise be content noise.
 It accepts Variant P schemas 0-2. Variant Q requires a different model, and
 schema 3 is rejected at the measured precision threshold. Its NumPy 1.x runtime
 limits the extra to Python 3.11-3.12; the rest of the package remains supported
-through Python 3.14. Through 0.29.0 the extra also resolves lightning 2.6.5
+through Python 3.14. The current TrustMark dependency line also resolves lightning 2.6.5
 (PYSEC-2026-3624, no fixed release yet); the vulnerable `load_from_checkpoint`
 path is unreachable here because TrustMark loads its checksummed checkpoints
 with plain `torch.load`. Bump lightning and cut a patch release when a fix
diff --git a/docs/module-internals.md b/docs/module-internals.md
index b664e8a..4d9dd5d 100644
--- a/docs/module-internals.md
+++ b/docs/module-internals.md
@@ -746,9 +746,9 @@ capture-less pill is too weak to attribute.
 
 The set of marks that veto the pill is DERIVED from the registry rows: every mark
 under the same label regime (`tc260`) belonging to a different product. It used to
-be a hand-written list of keys, and that list drifted -- LibLibAI was registered
-alongside RunningHub and Baidu, both of which were added to it, and LibLibAI was
-not, so a confident LibLibAI detection did not suppress the pill the way its two
+be a hand-written list of keys, and that list drifted -- LiblibAI was registered
+alongside RunningHub and Baidu, both of which were added to it, and LiblibAI was
+not, so a confident LiblibAI detection did not suppress the pill the way its two
 siblings did. Marks outside the TC260 regime (Gemini, Samsung) are deliberately
 not vetoers: neither can put `jimeng` into `provenance`, so neither can enable the
 arm it would be vetoing.
@@ -818,7 +818,7 @@ were briefly skipped there for exactly that reason.
 A mark whose removable footprint differs from what the detector localizes
 overrides `_footprint_rect` (which policy) and `_extend_match_box` (how far the
 box grows), not the whole `footprint_mask`. Baidu extends right to the corner tag
-and LibLibAI extends left to the triangle logo; both inherit every guard around
+and LiblibAI extends left to the triangle logo; both inherit every guard around
 that arithmetic.
 
 Yuanbao uses the polarity-independent `contrast` front end because its standard
@@ -1020,11 +1020,13 @@ Validation happens before model loading. The library never treats OCR confidence
 verification, and geometry-only operators do not need to invent text or script fields.
 
 When enabled, `QwenZImagePipeline` reconstructs the source once through its already
-loaded Qwen VAE, runs the ordinary global and face stages, blends 15% of the VAE
-reconstruction into that clean result, and calls the shared restoration compositor.
-The compositor derives binary source and candidate silhouettes, groups nearby lines,
-uses LaMa for the initial and residual-glyph erase passes, paints fresh silhouette
-edges, then copies the Qwen-VAE core with a 0.5-pixel feather. The evaluation script
+loaded Qwen VAE, runs the ordinary global and face stages, and calls the shared
+restoration compositor. The optional fidelity anchor first blends 15% of the VAE
+reconstruction into the clean result; it is off by default because the blend returned
+detector-visible OpenAI SynthID in the measured poster fixtures. The compositor derives
+binary source and candidate silhouettes, groups nearby lines, uses LaMa for the initial
+and residual-glyph erase passes, paints fresh silhouette edges, then copies the Qwen-VAE
+core with a 0.5-pixel feather. The evaluation script
 imports these same mask and compositing helpers so the two implementations cannot
 silently drift. Silhouette crops start 12% of line height beyond each horizontal
 side, then expand each side independently while a foreground component anchored
diff --git a/docs/python-api.md b/docs/python-api.md
index a0f8992..ff1d2a2 100644
--- a/docs/python-api.md
+++ b/docs/python-api.md
@@ -644,10 +644,10 @@ engine.remove_watermark(
 Install `remove-ai-watermarks[text-restoration]`. The manifest schema and safety
 constraints are documented in the CLI guide. The engine verifies its decoded RGB
 hash before loading the diffusion models and rejects SDXL, downscaling, and
-postprocessing combinations that were not evaluated. Tiling is allowed: the VAE
-donor uses the same overlapping tiles as the global pass. `InvisibleOptions` exposes the
-same field for `remove_all`; after a visible-stage edit, the manifest must be built
-against the staged pixels rather than the pristine source.
+postprocessing combinations that were not evaluated. Tiling is also rejected because
+the combined tiled-restoration path has no provider-oracle calibration. `InvisibleOptions`
+exposes the same field for `remove_all`; after a visible-stage edit, the manifest must
+be built against the staged pixels rather than the pristine source.
 
 Use manifest schema 1 for manually reviewed text plus script metadata. Automated
 operators that verify only text-region geometry should emit schema 2 lines with a
diff --git a/docs/supported-signals.md b/docs/supported-signals.md
index 7aa60c1..96eb44e 100644
--- a/docs/supported-signals.md
+++ b/docs/supported-signals.md
@@ -19,7 +19,7 @@ The `visible` command registers these mark keys:
 | `samsung` | `✦ Contenuti generati dall'AI` | Bottom left | Calibrated for the Italian text variant. |
 | `runninghub` | `RunningHub AI生成` | Top left | Strict visual and position gates. |
 | `baidu` | `百度 AI生成` | Bottom right | Detector and extended removal footprint. |
-| `liblib` | `LibLibAI` | Bottom center | Includes a minimum image size gate. |
+| `liblib` | `LiblibAI` | Bottom center | Includes a minimum image size gate. |
 | `jimeng_pill` | `AI生成` pill | Top left | Weak detector with additional product and background gates. |
 
 `--mark auto` evaluates all registered marks and removes every selected match.
@@ -226,7 +226,7 @@ not a universal clean verdict.
 | Kling | Kling image and video marks | No registered pixel decoder | TC260 AIGC |
 | Hailuo / MiniMax video | Hailuo composite video label | No registered pixel decoder | TC260 AIGC where present |
 | Baidu | Baidu mark | No registered pixel decoder | TC260 AIGC |
-| LibLibAI | LibLibAI mark | No registered pixel decoder | TC260 AIGC |
+| LiblibAI | LiblibAI mark | No registered pixel decoder | TC260 AIGC |
 | RunningHub | RunningHub mark | No registered pixel decoder | TC260 AIGC |
 | Samsung Galaxy AI | One locale specific mark | No registered pixel decoder | C2PA and Samsung markers |
 
diff --git a/docs/watermarking-landscape.md b/docs/watermarking-landscape.md
index 36703ef..3da0fec 100644
--- a/docs/watermarking-landscape.md
+++ b/docs/watermarking-landscape.md
@@ -58,7 +58,7 @@ defines two more native serializations. AVI stores an `AIGC` child in
 bounded RIFF and FLV readers validate the JSON field set and skip media
 payloads. Removal remuxes either container through ffmpeg with stream copy.
 
-- **HuggingFace-hosted job (caught by `metadata.huggingface_job`, surfaced by `identify` as the `hf_job` signal, MEDIUM confidence):** HuggingFace Jobs / Spaces can stamp generated PNGs with an `hf-job-id` tEXt chunk holding the job UUID. It marks the *hosting job*, not a model, so it lifts an Unknown verdict to a tentative AI via `hf_only` but never overrides a hard metadata signal. `_HF_JOB_CAVEAT` states the limit. Removal drops the chunk through the PNG metadata whitelist.
+- **Hugging Face-hosted job (caught by `metadata.huggingface_job`, surfaced by `identify` as the `hf_job` signal, MEDIUM confidence):** Hugging Face Jobs / Spaces can stamp generated PNGs with an `hf-job-id` tEXt chunk holding the job UUID. It marks the *hosting job*, not a model, so it lifts an Unknown verdict to a tentative AI via `hf_only` but never overrides a hard metadata signal. `_HF_JOB_CAVEAT` states the limit. Removal drops the chunk through the PNG metadata whitelist.
 - **No detectable signal on some downloads:** Recraft exports and some hosted
   FLUX surfaces can arrive without a supported local signal. Midjourney samples
   may carry IPTC metadata but no registered C2PA or pixel watermark. The open
diff --git a/scripts/README.md b/scripts/README.md
new file mode 100644
index 0000000..3cc35fd
--- /dev/null
+++ b/scripts/README.md
@@ -0,0 +1,68 @@
+# Maintainer scripts
+
+These scripts are development and evaluation tools, not installed CLI commands. Run
+them from the repository root with `uv run python scripts/<name>.py --help`. Inputs
+under `.local-eval/` and generated reports remain untracked unless a data README
+explicitly names a tracked canonical result.
+
+## Audits and release checks
+
+| Script | Purpose |
+| --- | --- |
+| `corpus_gap_scan.py` | Compare a local image corpus with the library's `identify` results. |
+| `detection_timing.py` | Record per-method metadata and verdict timings. |
+| `detection_timing_report.py` | Aggregate timing records by method and segment. |
+| `fidelity_metrics.py` | Compute objective image-fidelity metrics for paired outputs. |
+| `invisible_quality_audit.py` | Pair originals and invisible-removal outputs for quality review. |
+| `metadata_removal_audit.py` | Check metadata detection/removal parity over a corpus. |
+| `pill_gate_audit.py` | Measure the Jimeng pill detector on the product path. |
+| `real_examples_e2e.py` | Run end-to-end confidence checks over local examples. |
+| `record_parity_audit.py` | Compare record-based and file-based identification. |
+| `resource_ceilings.py` | Measure peak RSS and runtime for fill backends. |
+| `robustness_suite.py` | Exercise CLI failures on adversarial and degenerate inputs. |
+| `sidecar_regression.py` | Compare current identification with recorded sidecars. |
+| `smoke_matrix.py` | Exercise CLI parameter choices on real local data. |
+| `video_fidelity_probe.py` | Compare delivered video fidelity with its source. |
+| `visible_eval.py` | Benchmark registered visible-mark detectors. |
+| `visible_removal_audit.py` | Audit visible-removal results over a local corpus. |
+
+## Calibration and corpus preparation
+
+| Script | Purpose |
+| --- | --- |
+| `contentseal_transforms.py` | Reproduce and hash-check deterministic Content Seal variants. |
+| `detector_response.py` | Measure detector response over mark size, contrast, background, and aspect. |
+| `fill_quality.py` | Measure visible-fill quality against constructed ground truth. |
+| `ladder_headroom.py` | Measure recall cost from the coarse scale ladder. |
+| `synthid_corpus.py` | Ingest and inspect the local SynthID reference corpus. |
+| `vendor_cohort_harvest.py` | Partition TC260 carriers by producer code. |
+| `vendor_mark_calibrate.py` | Calibrate a candidate vendor text detector. |
+| `visible_alpha_solve.py` | Rebuild visible-watermark alpha assets from controlled captures. |
+| `visible_groundtruth.py` | Consolidate blinded contact-sheet labels into ground truth. |
+| `visible_positives.py` | List corpus images carrying a registered visible mark. |
+| `visible_recall_sample.py` | Build an unbiased blinded sample for recall measurement. |
+| `visible_sheets.py` | Build blinded contact sheets for relaxation candidates. |
+
+## Research and diagnostic prototypes
+
+| Script | Purpose |
+| --- | --- |
+| `cjk_tail_probe.py` | Test a generic template for otherwise uncovered CJK labels. |
+| `controlnet_sweep.py` | Sweep the historical ControlNet removal prototype. |
+| `infer_text_lines.py` | Draft stable source-text lines without modifying pixels. |
+| `qwen_scrub_prototype.py` | Probe low-strength Qwen regeneration on a GPU. |
+| `selective_text_restoration.py` | Evaluate text restoration over a scrubbed image. |
+| `synthid_pixel_probe.py` | Run the experimental local SynthID carrier probe. |
+| `video_synthid_sweep.py` | Build oracle-gated video regeneration candidates. |
+
+## Generated assets
+
+| Script | Purpose |
+| --- | --- |
+| `render_pill_silhouette.py` | Render the synthetic Jimeng pill silhouette. |
+| `render_vendor_silhouettes.py` | Render synthetic vendor text-mark silhouettes. |
+
+## Shared helpers
+
+`_plain_console.py` provides plain-text fallbacks for Rich output, and
+`_text_eval.py` contains normalization helpers shared by text-evaluation scripts.
diff --git a/scripts/contentseal_transforms.py b/scripts/contentseal_transforms.py
new file mode 100644
index 0000000..7c97ddf
--- /dev/null
+++ b/scripts/contentseal_transforms.py
@@ -0,0 +1,82 @@
+#!/usr/bin/env python3
+"""Reproduce the deterministic Content Seal crop, resize, and JPEG variants."""
+
+from __future__ import annotations
+
+import argparse
+import csv
+import hashlib
+import logging
+from pathlib import Path
+
+from PIL import Image
+
+log = logging.getLogger(__name__)
+
+ROOT = Path(__file__).resolve().parents[1]
+CORPUS = ROOT / "data" / "contentseal"
+MANIFEST = CORPUS / "manifest.csv"
+
+
+def _rows() -> dict[str, dict[str, str]]:
+    with MANIFEST.open(newline="", encoding="utf-8") as stream:
+        return {row["name"]: row for row in csv.DictReader(stream)}
+
+
+def _write_and_verify(image: Image.Image, path: Path, row: dict[str, str], *, format: str, quality: int) -> None:
+    image.save(path, format=format, quality=quality)
+    digest = hashlib.sha256(path.read_bytes()).hexdigest()
+    if digest != row["sha256"]:
+        raise RuntimeError(f"{row['name']} hash mismatch: expected {row['sha256']}, got {digest}")
+    log.info("Verified %s", path)
+
+
+def reproduce_transforms(output_dir: Path) -> list[Path]:
+    """Write and hash-check the eight deterministic manifest variants."""
+    rows = _rows()
+    output_dir.mkdir(parents=True, exist_ok=True)
+    outputs: list[Path] = []
+
+    for prefix, source_name in (("fox", "gen_fox_forest"), ("text", "gen_text_poster")):
+        with Image.open(CORPUS / rows[source_name]["file"]) as opened:
+            source = opened.convert("RGB")
+
+        for fraction in (0.5, 0.33):
+            width = int(source.width * fraction)
+            height = int(source.height * fraction)
+            left = (source.width - width) // 2
+            top = (source.height - height) // 2
+            name = f"{prefix}_crop{int(fraction * 100)}"
+            path = output_dir / f"{name}.webp"
+            crop = source.crop((left, top, left + width, top + height))
+            _write_and_verify(crop, path, rows[name], format="WEBP", quality=95)
+            outputs.append(path)
+
+        scale = 512 / max(source.size)
+        resized = source.resize(
+            (round(source.width * scale), round(source.height * scale)),
+            Image.Resampling.LANCZOS,
+        )
+        name = f"{prefix}_res512"
+        path = output_dir / f"{name}.webp"
+        _write_and_verify(resized, path, rows[name], format="WEBP", quality=95)
+        outputs.append(path)
+
+        name = f"{prefix}_jpeg85"
+        path = output_dir / f"{name}.jpg"
+        _write_and_verify(source, path, rows[name], format="JPEG", quality=85)
+        outputs.append(path)
+
+    return outputs
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("output_dir", type=Path, help="Directory for regenerated variants")
+    args = parser.parse_args()
+    logging.basicConfig(level=logging.INFO, format="%(levelname)s: %(message)s")
+    reproduce_transforms(args.output_dir)
+
+
+if __name__ == "__main__":
+    main()
diff --git a/scripts/visible_groundtruth.py b/scripts/visible_groundtruth.py
index 4372945..ea81c69 100644
--- a/scripts/visible_groundtruth.py
+++ b/scripts/visible_groundtruth.py
@@ -21,9 +21,9 @@ honest doubt never becomes a fabricated data point.
 
 from __future__ import annotations
 
+import argparse
 import csv
 import json
-import sys
 from pathlib import Path
 
 SEEN_TO_MARK = {
@@ -77,7 +77,15 @@ def metadata_provenance(path: str) -> list[str]:
 
 
 def main() -> None:
-    root = Path(sys.argv[1] if len(sys.argv) > 1 else ".local-eval/textmark-relaxation")
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument(
+        "root",
+        type=Path,
+        nargs="?",
+        default=Path(".local-eval/textmark-relaxation"),
+        help="Directory containing the blinded labelling rounds",
+    )
+    root = parser.parse_args().root
     out = root / "groundtruth.jsonl"
     rows: dict[str, dict] = {}
     stats: dict[str, int] = {}
diff --git a/scripts/visible_recall_sample.py b/scripts/visible_recall_sample.py
index 5be5941..8117726 100644
--- a/scripts/visible_recall_sample.py
+++ b/scripts/visible_recall_sample.py
@@ -22,10 +22,10 @@ Design decisions that matter:
 
 from __future__ import annotations
 
+import argparse
 import csv
 import json
 import random
-import sys
 from pathlib import Path
 from typing import TYPE_CHECKING, Any
 
@@ -35,6 +35,8 @@ import numpy as np
 if TYPE_CHECKING:
     from numpy.typing import NDArray
 
+import sys
+
 sys.path.insert(0, str(Path(__file__).parent.parent / "src"))
 from remove_ai_watermarks.image_io import imread
 
@@ -63,10 +65,16 @@ def corner_strip(img: NDArray[Any]) -> NDArray[Any] | None:
 
 
 def main() -> None:
-    scan = Path(sys.argv[1])
-    out = Path(sys.argv[2])
-    n_tc260 = int(sys.argv[3]) if len(sys.argv) > 3 else 160
-    n_google = int(sys.argv[4]) if len(sys.argv) > 4 else 80
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("scan", type=Path, help="JSONL corpus scan produced by the visible evaluation harness")
+    parser.add_argument("output", type=Path, help="Directory for contact sheets and the blinded manifest")
+    parser.add_argument("--tc260", type=int, default=160, help="Number of TC260 carriers to sample")
+    parser.add_argument("--google", type=int, default=80, help="Number of Google-provenance carriers to sample")
+    args = parser.parse_args()
+    scan = args.scan
+    out = args.output
+    n_tc260 = args.tc260
+    n_google = args.google
     out.mkdir(parents=True, exist_ok=True)
 
     recs = [json.loads(line) for line in scan.open() if '"marks"' in line]
diff --git a/scripts/visible_sheets.py b/scripts/visible_sheets.py
index 2c70cef..a01d633 100644
--- a/scripts/visible_sheets.py
+++ b/scripts/visible_sheets.py
@@ -12,6 +12,7 @@ Each sheet mixes three strata in shuffled order:
 The two control strata are what make a low measured precision trustworthy.
 """
 
+import argparse
 import csv
 import json
 import random
@@ -62,9 +63,13 @@ def crop(path: str, region: tuple[int, int, int, int] | None, pad_factor: float
 
 
 def main() -> None:
-    with open(sys.argv[1]) as fh:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument("input", type=Path, help="JSON candidate list")
+    parser.add_argument("output", type=Path, help="Directory for blinded contact sheets")
+    args = parser.parse_args()
+    with args.input.open() as fh:
         items = json.load(fh)  # [{uid,path,key,stratum,conf}]
-    outdir = Path(sys.argv[2])
+    outdir = args.output
     outdir.mkdir(parents=True, exist_ok=True)
     random.Random(1234).shuffle(items)  # noqa: S311 -- sheet ordering, not cryptography
 
diff --git a/src/remove_ai_watermarks/_internal/c2pa.py b/src/remove_ai_watermarks/_internal/c2pa.py
index 38ee185..b933b3a 100644
--- a/src/remove_ai_watermarks/_internal/c2pa.py
+++ b/src/remove_ai_watermarks/_internal/c2pa.py
@@ -624,16 +624,16 @@ def _populate_registry_fields(buffer: bytes, info: dict[str, Any]) -> bool:
 
     if b"c2pa.watermarked" in buffer:
         info["watermarked"] = True
+    soft_bindings = soft_binding_vendors_in(buffer)
     synthid = (
         []
-        if soft_binding_vendors_in(buffer)
+        if soft_bindings
         else synthid_evidence_vendors_in(buffer, has_watermark_action=info.get("watermarked", False))
     )
     if ai_source and synthid:
         info["synthid_vendors"] = synthid
         info["synthid_watermark"] = synthid_verdict(", ".join(synthid))
 
-    soft_bindings = soft_binding_vendors_in(buffer)
     if soft_bindings:
         info["soft_binding_vendors"] = soft_bindings
         info["soft_binding"] = ", ".join(soft_bindings)
diff --git a/src/remove_ai_watermarks/_internal/constants.py b/src/remove_ai_watermarks/_internal/constants.py
index 7f7f416..de0fe00 100644
--- a/src/remove_ai_watermarks/_internal/constants.py
+++ b/src/remove_ai_watermarks/_internal/constants.py
@@ -70,7 +70,7 @@ C2PA_AI_VENDORS: tuple[C2paAiVendor, ...] = (
     _vendor(
         b"OpenAI",
         "OpenAI",
-        "OpenAI (ChatGPT / gpt-image / DALL-E / Sora)",
+        "OpenAI (ChatGPT / GPT Image / DALL·E / Sora)",
         "OpenAI",
         synthid=True,
         synthid_requires_watermark_action=True,
@@ -128,8 +128,8 @@ C2PA_AI_TOOLS = {
         ("GPT-4o", "GPT-4o"),
         ("ChatGPT", "ChatGPT"),
         ("Sora", "Sora"),
-        ("DALL-E", "DALL-E"),
-        ("DALL", "DALL-E"),
+        ("DALL-E", "DALL·E"),
+        ("DALL", "DALL·E"),
         ("Imagen", "Imagen"),
         ("Firefly", "Firefly"),
         ("Dreamina", "Dreamina"),
@@ -138,16 +138,18 @@ C2PA_AI_TOOLS = {
 
 C2PA_SOFT_BINDINGS = {
     b"com.adobe.trustmark": "Adobe TrustMark",
-    b"com.adobe.icn": "Adobe (content fingerprint)",
-    b"com.digimarc": "Digimarc",
+    b"com.adobe.icn": "Adobe Image Comparator Network",
+    b"com.digimarc": "Digimarc Validate",
     b"com.imatag.lamark": "Imatag (Lamark)",
     b"ai.steg": "Steg.AI",
     b"com.microsoft.invismark": "Microsoft InvisMark",
     b"com.microsoft.wavmark": "Microsoft WavMark",
     b"com.verimatrix": "Verimatrix",
     b"com.nagra.nexguard": "NAGRA NexGuard",
-    b"com.aiwatermark": "AIWatermark (Meta PixelSeal)",
-    b"ai.trufo": "Trufo",
+    b"com.aiwatermark.pixelseal": "AIWatermark PixelSeal",
+    b"com.aiwatermark.videoseal": "AIWatermark VideoSeal",
+    b"com.aiwatermark.audioseal": "AIWatermark AudioSeal",
+    b"ai.trufo": "Trufo PawPrint",
     b"app.overlai": "Overlai",
     b"com.markany": "MarkAny",
     b"com.mentaport": "Mentaport",
diff --git a/src/remove_ai_watermarks/_internal/qwen_zimage_pipeline.py b/src/remove_ai_watermarks/_internal/qwen_zimage_pipeline.py
index 9cda34e..57d6eac 100644
--- a/src/remove_ai_watermarks/_internal/qwen_zimage_pipeline.py
+++ b/src/remove_ai_watermarks/_internal/qwen_zimage_pipeline.py
@@ -1074,29 +1074,14 @@ class QwenZImagePipeline:
         fidelity_anchor: bool = False,
     ) -> Image.Image:
         """Execute global regeneration and masked face repair."""
+        if text_manifest is not None and tile:
+            raise ValueError("Verified text restoration is not calibrated with tiled diffusion")
         self._require_cuda()
         seed = resolve_seed(seed)
         donor = None
         if text_manifest is not None:
             self._progress("Reconstructing the verified text donor with the Qwen VAE...")
-            if tile and max(image.size) > tile_size:
-                from remove_ai_watermarks._internal.tiling import run_tiled
-
-                donor = run_tiled(
-                    self._qwen_vae_roundtrip,
-                    image,
-                    tile_size,
-                    tile_overlap,
-                    lambda message: self._progress(
-                        message.replace(
-                            "Tiled diffusion",
-                            "Reconstructing the verified text donor",
-                            1,
-                        )
-                    ),
-                )
-            else:
-                donor = self._qwen_vae_roundtrip(image)
+            donor = self._qwen_vae_roundtrip(image)
         global_strength = (
             resolution_adaptive_denoise(image.width, image.height) if strength is None else float(strength)
         )
diff --git a/src/remove_ai_watermarks/_text_mark_engine.py b/src/remove_ai_watermarks/_text_mark_engine.py
index c9dd02a..4c29dab 100644
--- a/src/remove_ai_watermarks/_text_mark_engine.py
+++ b/src/remove_ai_watermarks/_text_mark_engine.py
@@ -90,7 +90,7 @@ class TextMarkConfig:
     asset_name: str  # bundled alpha PNG under assets/ (e.g. "doubao_alpha.png")
     corner: Literal[
         "br", "bl", "tl", "bc"
-    ]  # bottom-right (Doubao/Jimeng), bottom-left (Samsung), top-left (RunningHub), bottom-center (LibLibAI)
+    ]  # bottom-right (Doubao/Jimeng), bottom-left (Samsung), top-left (RunningHub), bottom-center (LiblibAI)
     margin_floor: int  # min margin in px for locate (4 for br marks, 2 for Samsung)
     # locate geometry (fraction of scale_base -- see scale_base())
     width_frac: float
@@ -695,7 +695,7 @@ class TextMarkEngine:
 
         OVERRIDABLE, and the override contract is specifically the DETECTOR'S MATCH BOX:
         a mark whose removable footprint reaches beyond what the NCC localizes -- Baidu's
-        flat white tag right of the text run, LibLibAI's triangle logo left of the
+        flat white tag right of the text run, LiblibAI's triangle logo left of the
         wordmark -- supplies its own extension here and inherits the rest of the
         footprint path. The blob-bbox branch never routes through an override.
         """
@@ -771,7 +771,7 @@ class TextMarkEngine:
         """Footprint policy for a mark whose fill must be bounded by the DETECTOR's match
         box and never by the binary glyph blob.
 
-        Baidu's white tag has a flat interior a top-hat cannot answer, and LibLibAI's
+        Baidu's white tag has a flat interior a top-hat cannot answer, and LiblibAI's
         blob bleeds up into background structure; in both cases the blob bbox is
         measurably wrong and the NCC match box is right. ``force`` takes priority here,
         unlike the default policy: a ``--no-detect`` caller named the mark, so the whole
diff --git a/src/remove_ai_watermarks/api.py b/src/remove_ai_watermarks/api.py
index 84d2ccb..757907b 100644
--- a/src/remove_ai_watermarks/api.py
+++ b/src/remove_ai_watermarks/api.py
@@ -157,7 +157,7 @@ def remove_visible(
     """Remove every detected known visible AI mark through localize then fill.
 
     The registry currently covers the Gemini sparkle; Doubao, Jimeng, Qwen, Kling,
-    Yuanbao, Samsung, RunningHub, Baidu, and LibLibAI text marks; and the Jimeng
+    Yuanbao, Samsung, RunningHub, Baidu, and LiblibAI text marks; and the Jimeng
     pill. Returns ``(result_bgr, [labels removed])``.
 
     ``source`` is a file path OR a BGR ndarray. For a PATH, metadata provenance is read
diff --git a/src/remove_ai_watermarks/cli.py b/src/remove_ai_watermarks/cli.py
index fc99622..55874be 100644
--- a/src/remove_ai_watermarks/cli.py
+++ b/src/remove_ai_watermarks/cli.py
@@ -307,7 +307,7 @@ _seed_option = click.option(
     help="Random seed for reproducibility. Default 0: both profiles are certified "
     "at a fixed seed, because SynthID removal near the strength floor is seed-dependent.",
 )
-_hf_token_option = click.option("--hf-token", type=str, default=None, help="HuggingFace API token.")
+_hf_token_option = click.option("--hf-token", type=str, default=None, help="Hugging Face API token.")
 _humanize_option = click.option(
     "--humanize", type=float, default=0.0, help="Analog Humanizer film grain intensity (0 = off, typical: 2.0-6.0)."
 )
@@ -859,7 +859,7 @@ def cmd_invisible(
     text_manifest: Path | None,
     fidelity_anchor: bool,
 ) -> None:
-    """Remove invisible AI watermarks (SynthID, StableSignature, TreeRing).
+    """Attempt to disrupt invisible AI watermarks through pixel regeneration.
 
     Regenerates the pixels with the two-stage diffusion profile. CUDA-only:
     pip install 'remove-ai-watermarks[qwen-zimage]'
@@ -1001,8 +1001,8 @@ def cmd_metadata(
     Strips EXIF AI tags, PNG text chunks, C2PA provenance manifests, and the
     China TC260 AIGC label. Beyond images (PNG/JPEG/WebP/AVIF/HEIF/JXL) it also
     strips provenance metadata from MP4/MOV/M4V/M4A containers and, via ffmpeg,
-    from WebM/MKV/AVI/FLV/MP3/WAV/FLAC/OGG. The coded image, audio, and video
-    data are left untouched.
+    from WebM/MKV/MKA/AVI/FLV/MP3/WAV/FLAC/OGG/OGA/Opus/AAC. The coded image,
+    audio, and video data are left untouched.
     """
     from remove_ai_watermarks.metadata import get_ai_metadata, has_ai_metadata, strip_and_verify
 
diff --git a/src/remove_ai_watermarks/identify.py b/src/remove_ai_watermarks/identify.py
index ea3fea2..442d139 100644
--- a/src/remove_ai_watermarks/identify.py
+++ b/src/remove_ai_watermarks/identify.py
@@ -145,7 +145,7 @@ _INVISIBLE_WM_CAVEAT = (
     "or resizing, so it confirms origin only on a pristine (un-re-encoded) file."
 )
 _HF_JOB_CAVEAT = (
-    "The hf-job-id tag marks a HuggingFace-hosted job (commonly diffusion "
+    "The hf-job-id tag marks a Hugging Face-hosted job (commonly diffusion "
     "generation) but names neither the model nor the content type, so it is a "
     "medium-confidence signal, not proof the pixels are AI-generated."
 )
@@ -445,7 +445,7 @@ def evidence_from_metadata_record(
     if iptc_system:
         ai_metadata.setdefault("ai_system", f"IPTC 2025.1 AI disclosure ({iptc_system})")
     if hf_job:
-        ai_metadata.setdefault("huggingface_job", f"HuggingFace-hosted job ({hf_job})")
+        ai_metadata.setdefault("huggingface_job", f"Hugging Face-hosted job ({hf_job})")
     if samsung is not None:
         ai_metadata.setdefault("samsung_genai", f"Samsung Galaxy AI editing marker (genAIType={samsung})")
 
@@ -953,7 +953,7 @@ def _visible_sparkle(image_path: Path, *, image: NDArray[Any] | None = None) ->
 # metadata label); the per-engine detection thresholds live in the registry.
 # Text mark -> the platform sentence this report prints when that mark is the strongest
 # evidence, DERIVED from the registry rows so registering a mark is one edit. It was a
-# hand-maintained copy, and that class of copy is how LibLibAI ended up registered but
+# hand-maintained copy, and that class of copy is how LiblibAI ended up registered but
 # missing from the pill veto. Insertion order is the registry's, which is what fixes the
 # scan order below. The Gemini sparkle and the capture-less pill carry no platform of
 # their own (`KnownMark.platform is None`) and are excluded here: the sparkle has its
@@ -1426,17 +1426,17 @@ def _identify_from_evidence(
             platform = "xAI (Grok / Aurora)"
         ai_vendor_claims["xai"] = "xAI"
 
-    # ── HuggingFace-hosted job marker (hf-job-id PNG text chunk) ─────
+    # ── Hugging Face-hosted job marker (hf-job-id PNG text chunk) ─────
     # Marks the hosting job, not a model -- medium confidence (commonly diffusion
     # output). Like the visible sparkle, it lifts an otherwise-Unknown verdict to
     # a tentative AI, but never overrides a high-confidence metadata signal.
     hf_job = evidence.huggingface_job
     if hf_job:
-        signals.append(Signal("hf_job", f"HuggingFace job {hf_job}", "medium"))
-        watermarks.append("HuggingFace-hosted job (hf-job-id)")
+        signals.append(Signal("hf_job", f"Hugging Face job {hf_job}", "medium"))
+        watermarks.append("Hugging Face-hosted job (hf-job-id)")
         caveats.append(_HF_JOB_CAVEAT)
         if platform is None:
-            platform = "HuggingFace-hosted job (model not identified)"
+            platform = "Hugging Face-hosted job (model not identified)"
 
     # ── Samsung Galaxy AI editing marker (genAIType) ─────────────────
     # Galaxy AI tools stamp a proprietary genAIType in PhotoEditor_Re_Edit_Data.
diff --git a/src/remove_ai_watermarks/invisible_engine.py b/src/remove_ai_watermarks/invisible_engine.py
index cdf9c1e..e2ea1c4 100644
--- a/src/remove_ai_watermarks/invisible_engine.py
+++ b/src/remove_ai_watermarks/invisible_engine.py
@@ -33,7 +33,7 @@ warnings.filterwarnings("ignore", category=UserWarning, module="huggingface_hub"
 warnings.filterwarnings("ignore", category=UserWarning, module="diffusers")
 warnings.filterwarnings("ignore", module="transformers")
 
-# Suppress HuggingFace internal logging
+# Suppress Hugging Face internal logging
 os.environ["TRANSFORMERS_VERBOSITY"] = "error"
 os.environ["DIFFUSERS_VERBOSITY"] = "error"
 
@@ -104,7 +104,7 @@ class InvisibleEngine:
                 global pass, vendor-adaptive strength because an SDXL global stage
                 needs more of it). BOTH ARE CUDA-ONLY -- there is no CPU or MPS path
                 for invisible-watermark removal.
-            hf_token: HuggingFace API token.
+            hf_token: Hugging Face API token.
             progress_callback: Optional callback for progress messages.
             controlnet_conditioning_scale: Canny ControlNet structure-preservation
                 strength on the global stage of both profiles.
@@ -187,9 +187,8 @@ class InvisibleEngine:
                 pixels. Enables the experimental Qwen-VAE ``vae-glyphs`` post-pass.
                 Requires the ``text-restoration`` extra and the ``qwen-zimage``
                 profile. Incompatible with downscaling, humanize, unsharp, and
-                adaptive polish. Tiling is supported: the VAE donor uses the same
-                overlapping tiles as the global pass, then glyph restore runs on
-                the blended full frame.
+                adaptive polish. Tiling is rejected because that combination has
+                no provider-oracle calibration.
             fidelity_anchor: Blend 15% of the Qwen-VAE donor across the whole frame
                 before glyph restoration. OFF by default since 0.27.1: that global
                 blend was measured to return detector-visible OpenAI SynthID on
@@ -211,6 +210,8 @@ class InvisibleEngine:
         if text_manifest is not None:
             if self._remover.model_profile != QWEN_ZIMAGE_PROFILE:
                 raise ValueError("--text-manifest is supported only by the qwen-zimage profile")
+            if tile:
+                raise ValueError("--text-manifest is not calibrated with --tile")
             if max_resolution != 0:
                 raise ValueError("--text-manifest requires --max-resolution 0")
             if humanize > 0.0 or unsharp > 0.0 or adaptive_polish:
diff --git a/src/remove_ai_watermarks/liblib_engine.py b/src/remove_ai_watermarks/liblib_engine.py
index af6c4be..0eee574 100644
--- a/src/remove_ai_watermarks/liblib_engine.py
+++ b/src/remove_ai_watermarks/liblib_engine.py
@@ -1,13 +1,13 @@
-"""LibLibAI visible watermark detector/localizer.
+"""LiblibAI visible watermark detector/localizer.
 
-LibLibAI (哩布哩布AI, USCC 91110105MACJ6K1C8A) stamps its generations with a
-white triangle logo + "LibLibAI" latin wordmark at **bottom-center** (not a
+LiblibAI (哩布哩布AI, USCC 91110105MACJ6K1C8A) stamps its generations with a
+white triangle logo + "LiblibAI" Latin wordmark at **bottom-center** (not a
 corner -- the locate box is horizontally centered). Detection matches the
-bundled font-rendered "LibLibAI" silhouette (the triangle logo is NOT rendered
+bundled font-rendered "LiblibAI" silhouette (the triangle logo is NOT rendered
 -- logos vary, the wordmark discriminates); removal is the shared **localize ->
 fill** (the glyph blob covers logo + wordmark, both bright).
 
-This module supplies only LibLibAI's tuned :class:`TextMarkConfig`
+This module supplies only LiblibAI's tuned :class:`TextMarkConfig`
 (``assets/liblib_alpha.png`` from ``scripts/render_vendor_silhouettes.py``,
 never cut from an upload).
 
@@ -64,7 +64,7 @@ _ALPHA_HEIGHT_FRAC = 0.026
 _LADDER = (0.9, 1.0, 1.1)
 
 _CONFIG = TextMarkConfig(
-    name="LibLibAI",
+    name="LiblibAI",
     asset_name="liblib_alpha.png",
     corner="bc",
     margin_floor=4,
@@ -90,12 +90,12 @@ _CONFIG = TextMarkConfig(
 
 
 def _alpha_template() -> NDArray[Any] | None:
-    """The bundled LibLibAI alpha template (float [0,1]), or None."""
+    """The bundled LiblibAI alpha template (float [0,1]), or None."""
     return _text_mark_engine.load_alpha_template(_CONFIG.asset_name)
 
 
 class LibLibEngine(TextMarkEngine):
-    """Detect/localize the visible LibLibAI wordmark (bottom-center; localize -> fill)."""
+    """Detect/localize the visible LiblibAI wordmark (bottom-center; localize -> fill)."""
 
     # Per-mark size floor prevents small generic icons from matching the wordmark.
     _MIN_SHORT_SIDE = 480
diff --git a/src/remove_ai_watermarks/metadata.py b/src/remove_ai_watermarks/metadata.py
index 981d216..90379c0 100644
--- a/src/remove_ai_watermarks/metadata.py
+++ b/src/remove_ai_watermarks/metadata.py
@@ -199,7 +199,7 @@ def parse_tc260_aigc_json(value: bytes) -> dict[str, str] | None:
     return fields if TC260_AIGC_FIELDS & fields.keys() else None
 
 
-# HuggingFace-hosted GPU jobs (Jobs / Spaces) stamp generated PNGs with this
+# Hugging Face-hosted GPU jobs (Jobs / Spaces) stamp generated PNGs with this
 # ``tEXt`` chunk key holding the job UUID. It marks the hosting job, not a
 # specific model -- a medium-confidence AI signal (commonly diffusion output).
 _HF_JOB_KEY: str = "hf-job-id"
@@ -510,7 +510,7 @@ def has_ai_metadata(image_path: Path) -> bool:
     # only the XMP form; the raw-JSON tEXt chunk needs the PIL-based parse).
     if aigc_label(image_path) is not None:
         return True
-    # HuggingFace-hosted job marker (hf-job-id PNG text chunk).
+    # Hugging Face-hosted job marker (hf-job-id PNG text chunk).
     if huggingface_job(image_path):
         return True
     # xAI / Grok: no C2PA/IPTC/XMP -- only the EXIF Signature + UUID-Artist pair.
@@ -682,10 +682,10 @@ def c2pa_cloud_manifest(image_path: Path) -> str | None:
 
 
 def _huggingface_job_impl(image_path: Path) -> str | None:
-    """Return the HuggingFace job id if the image carries an ``hf-job-id`` PNG
+    """Return the Hugging Face job id if the image carries an ``hf-job-id`` PNG
     text chunk, else None.
 
-    HuggingFace-hosted GPU jobs (Jobs / Spaces) stamp generated PNGs with an
+    Hugging Face-hosted GPU jobs (Jobs / Spaces) stamp generated PNGs with an
     ``hf-job-id`` ``tEXt`` chunk holding the job's UUID. It identifies the
     *hosting job*, not a specific model, and is most commonly seen on diffusion-
     generation output -- a medium-confidence AI signal, not proof of AI pixels
@@ -1216,9 +1216,9 @@ def get_ai_metadata(image_path: Path) -> dict[str, str]:
     if system := iptc_ai_system(image_path):
         result.setdefault("ai_system", f"IPTC 2025.1 AI disclosure ({system})")
 
-    # HuggingFace-hosted job marker (hf-job-id PNG text chunk).
+    # Hugging Face-hosted job marker (hf-job-id PNG text chunk).
     if job := huggingface_job(image_path):
-        result.setdefault("huggingface_job", f"HuggingFace-hosted job ({job})")
+        result.setdefault("huggingface_job", f"Hugging Face-hosted job ({job})")
     # Samsung Galaxy AI editing marker (genAIType in PhotoEditor_Re_Edit_Data).
     if (genai := samsung_genai(image_path)) is not None:
         result.setdefault("samsung_genai", f"Samsung Galaxy AI editing marker (genAIType={genai})")
diff --git a/src/remove_ai_watermarks/video.py b/src/remove_ai_watermarks/video.py
index 1b73018..c4716f0 100644
--- a/src/remove_ai_watermarks/video.py
+++ b/src/remove_ai_watermarks/video.py
@@ -179,8 +179,8 @@ _VISIBLE_PLATFORM = {
     "veo": "Google Veo",
     "seedance": "ByteDance Seedance",
     "dola": "ByteDance Dola",
-    "hailuo": "MiniMax Hailuo",
-    "kling": "Kuaishou Kling",
+    "hailuo": "MiniMax Hailuo AI",
+    "kling": "Kuaishou Kling AI",
 }
 
 
diff --git a/src/remove_ai_watermarks/watermark_registry.py b/src/remove_ai_watermarks/watermark_registry.py
index d116d45..086209e 100644
--- a/src/remove_ai_watermarks/watermark_registry.py
+++ b/src/remove_ai_watermarks/watermark_registry.py
@@ -17,17 +17,17 @@ localizer stays cheap (cv2/numpy, CPU) so a memory-tight caller can run it on a
 small worker; the heavy fill (MI-GAN / LaMa) is opt-in and chosen by the caller.
 
 Entries:
-  - ``gemini`` -- Google Gemini / Nano Banana sparkle, bottom-right.
+  - ``gemini`` -- Google Gemini / Nano Banana visible watermark (sparkle), bottom-right.
   - ``doubao`` -- ByteDance Doubao "豆包AI生成" text strip, bottom-right.
   - ``jimeng`` -- ByteDance Jimeng / Dreamina "★ 即梦AI" wordmark, bottom-right.
   - ``qwen`` -- Alibaba Qwen "千问AI生成" text strip, bottom-right.
-  - ``kling`` -- Kuaishou Kling "可灵AI 3.0" text strip, bottom-right.
+  - ``kling`` -- Kuaishou Kling AI "可灵AI 3.0" text strip, bottom-right.
   - ``yuanbao`` -- Tencent Yuanbao "元宝 / AI生成" two-line mark, bottom-right.
   - ``samsung`` -- Samsung Galaxy AI "Contenuti generati dall'AI" strip, bottom-left.
   - ``jimeng_pill`` -- Jimeng-basic "AI生成" pill, top-left (capture-less).
   - ``runninghub`` -- RunningHub "RunningHub AI生成" text, top-left (gray front-end).
   - ``baidu`` -- Baidu "百度 AI生成" text + white tag, bottom-right.
-  - ``liblib`` -- LibLibAI "LibLibAI" wordmark, bottom-center.
+  - ``liblib`` -- LiblibAI "LiblibAI" wordmark, bottom-center.
 """
 
 from __future__ import annotations
@@ -620,7 +620,7 @@ _REGISTRY: tuple[KnownMark, ...] = (
     # is None so it can never act as a TC260 sibling in _keep_pill.
     KnownMark(
         "gemini",
-        "Google Gemini sparkle",
+        "Google Gemini visible watermark (sparkle)",
         "bottom-right",
         True,
         "gemini",
@@ -656,9 +656,9 @@ _REGISTRY: tuple[KnownMark, ...] = (
     ),
     _text_mark(
         "kling",
-        "Kling 可灵AI 3.0 text",
+        "Kling AI 可灵AI 3.0 text",
         "bottom-right",
-        platform="Kuaishou Kling (visible 可灵AI 3.0 mark detected)",
+        platform="Kuaishou Kling AI (visible 可灵AI 3.0 mark detected)",
         tc260_producer_codes=("91110108335469089C",),
     ),
     _text_mark(
@@ -693,9 +693,9 @@ _REGISTRY: tuple[KnownMark, ...] = (
     ),
     _text_mark(
         "liblib",
-        "LibLibAI wordmark",
+        "LiblibAI wordmark",
         "bottom-center",
-        platform="LibLibAI (visible LibLibAI mark detected)",
+        platform="LiblibAI (visible LiblibAI mark detected)",
         tc260_producer_codes=("91110105MACJ6K1C8A",),
     ),
     # Same product as the Jimeng wordmark -- the one pair that cross-relaxes.
@@ -794,7 +794,7 @@ def tc260_producer_vendors() -> dict[str, str]:
 def _pill_suppressors() -> set[str]:
     """Marks whose detection vetoes the capture-less pill: same label regime as the
     pill, different product. Derived so a newly registered TC260 mark cannot be
-    forgotten here -- which is exactly how LibLibAI ended up missing."""
+    forgotten here -- which is exactly how LiblibAI ended up missing."""
     pill = get_mark("jimeng_pill")
     return {
         m.key
@@ -822,9 +822,9 @@ def _keep_pill(keys: set[str], *, provenance: frozenset[str], footprint_flat: bo
     No confirmation at all -> never remove (blocks false fires on non-Jimeng content).
 
     The suppressor set is DERIVED from the registry (same label regime, different
-    product), not hand-listed. The hand-written list had drifted: LibLibAI was
+    product), not hand-listed. The hand-written list had drifted: LiblibAI was
     registered alongside RunningHub and Baidu but never added to it, so a confident
-    LibLibAI detection did not veto the pill the way its two siblings did. Marks
+    LiblibAI detection did not veto the pill the way its two siblings did. Marks
     outside the TC260 regime (Gemini, Samsung) are deliberately NOT suppressors --
     neither can put ``"jimeng"`` into ``provenance``, so neither can enable the arm
     they would be vetoing."""
diff --git a/tests/test_contentseal_corpus.py b/tests/test_contentseal_corpus.py
index e6963e0..7ee107f 100644
--- a/tests/test_contentseal_corpus.py
+++ b/tests/test_contentseal_corpus.py
@@ -58,3 +58,12 @@ def test_default_pipeline_clearance_is_recorded() -> None:
     rows = {row["name"]: row for row in _manifest_rows()}
     for name in ("fox_modal_invisible", "text_modal_invisible"):
         assert rows[name]["oracle_verdict"] == "not_detected", name
+
+
+def test_deterministic_transforms_reproduce_recorded_hashes(tmp_path: Path) -> None:
+    from scripts.contentseal_transforms import reproduce_transforms
+
+    outputs = reproduce_transforms(tmp_path)
+
+    assert len(outputs) == 8
+    assert all(path.is_file() for path in outputs)
diff --git a/tests/test_designer_synthid_suppression.py b/tests/test_designer_synthid_suppression.py
index e549723..f1f7b22 100644
--- a/tests/test_designer_synthid_suppression.py
+++ b/tests/test_designer_synthid_suppression.py
@@ -34,7 +34,10 @@ DESIGNER_STORE = {
                 },
                 {
                     "label": "c2pa.soft-binding",
-                    "data": {"alg": "com.microsoft.invismark.1", "blocks": [{"value": "bf7a2993-cc1f-47e1-b1f0-cd8839aabb22"}]},
+                    "data": {
+                        "alg": "com.microsoft.invismark.1",
+                        "blocks": [{"value": "bf7a2993-cc1f-47e1-b1f0-cd8839aabb22"}],
+                    },
                 },
             ],
         }
diff --git a/tests/test_evaluation_data.py b/tests/test_evaluation_data.py
new file mode 100644
index 0000000..b0559da
--- /dev/null
+++ b/tests/test_evaluation_data.py
@@ -0,0 +1,23 @@
+"""Cross-corpus integrity checks for tracked evaluation tables."""
+
+from __future__ import annotations
+
+import csv
+import re
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[1]
+EVALUATIONS = ROOT / "data" / "evaluations"
+SHA256 = re.compile(r"^[0-9a-f]{64}$")
+
+
+def test_every_recorded_evaluation_sha256_is_well_formed() -> None:
+    checked = 0
+    for path in sorted(EVALUATIONS.rglob("*.csv")):
+        with path.open(newline="", encoding="utf-8") as stream:
+            for line_number, row in enumerate(csv.DictReader(stream), start=2):
+                for field, value in row.items():
+                    if field is not None and field.endswith("sha256") and value:
+                        assert SHA256.fullmatch(value), f"{path.relative_to(ROOT)}:{line_number} {field}={value!r}"
+                        checked += 1
+    assert checked > 0
diff --git a/tests/test_identify.py b/tests/test_identify.py
index 79575c2..8f01b39 100644
--- a/tests/test_identify.py
+++ b/tests/test_identify.py
@@ -703,7 +703,8 @@ class TestIdentifyRealSamples:
         )
         apple = tmp_path / "apple.jpg"
         apple.write_bytes(
-            b'\xff\xd8\xff\xe1<x:xmpmeta Iptc4xmpExt:DigitalSourceType="compositeWithTrainedAlgorithmicMedia" photoshop:Credit="Apple Photos Clean Up"></x:xmpmeta>\xff\xd9'
+            b'\xff\xd8\xff\xe1<x:xmpmeta Iptc4xmpExt:DigitalSourceType="compositeWithTrainedAlgorithmicMedia" '
+            b'photoshop:Credit="Apple Photos Clean Up"></x:xmpmeta>\xff\xd9'
         )
 
         assert identify(muse, check_visible=False, check_invisible=False).platform == (
diff --git a/tests/test_invisible_engine.py b/tests/test_invisible_engine.py
index b7fc46b..c14dfe6 100644
--- a/tests/test_invisible_engine.py
+++ b/tests/test_invisible_engine.py
@@ -60,6 +60,7 @@ class TestVerifiedTextMode:
         manifest.write_text("{}", encoding="utf-8")
         cases = (
             ("sdxl-zimage", {}, "qwen-zimage"),
+            ("qwen-zimage", {"tile": True}, "not calibrated with --tile"),
             ("qwen-zimage", {"max_resolution": 1024}, "max-resolution 0"),
             ("qwen-zimage", {"humanize": 1.0}, "humanize=0"),
             ("qwen-zimage", {"adaptive_polish": True}, "polish disabled"),
@@ -128,10 +129,6 @@ class TestVerifiedTextMode:
 
         assert seen["fidelity_anchor"] is True
 
-        engine.remove_watermark(source, output, text_manifest=manifest, tile=True)
-
-        assert seen["tile"] is True
-
 
 class TestNativeOutputSize:
     """Model-side latent-grid rounding must not change the public output size."""
diff --git a/tests/test_liblib_engine.py b/tests/test_liblib_engine.py
index 76ccff1..227040b 100644
--- a/tests/test_liblib_engine.py
+++ b/tests/test_liblib_engine.py
@@ -1,4 +1,4 @@
-"""Tests for the LibLibAI ("LibLibAI" wordmark) visible-watermark engine.
+"""Tests for the LiblibAI ("LiblibAI" wordmark) visible-watermark engine.
 
 Every tuned constant in ``liblib_engine`` was measured on the 15-frame vendor
 cohort (2026-07-22); these tests pin the load-bearing ones: the bottom-CENTER
@@ -24,7 +24,7 @@ _MARK_FRAC = 0.10  # measured wordmark width, fraction of the frame WIDTH
 
 
 def _compose(w: int, h: int, bg: float = 100.0):
-    """Composite a triangle logo + the LibLibAI wordmark, bottom-center."""
+    """Composite a triangle logo + the LiblibAI wordmark, bottom-center."""
     img = np.full((h, w, 3), bg, np.float32)
     at = _alpha_template()
     gw = int(_MARK_FRAC * w)
@@ -112,8 +112,8 @@ class TestDetectAndMask:
         assert eng.footprint_mask(img) is None
 
     def test_confident_liblib_detection_suppresses_the_jimeng_pill(self):
-        # A LibLibAI image is TC260 too but is not Jimeng-basic: like Doubao/Qwen/
-        # Kling/RunningHub/Baidu, a confident LibLibAI detection must veto the pill.
+        # A LiblibAI image is TC260 too but is not Jimeng-basic: like Doubao/Qwen/
+        # Kling/RunningHub/Baidu, a confident LiblibAI detection must veto the pill.
         # It was the one mark the hand-written veto list in ``_keep_pill`` missed.
         from remove_ai_watermarks.watermark_registry import _keep_pill
 
diff --git a/tests/test_qwen_zimage_pipeline.py b/tests/test_qwen_zimage_pipeline.py
index 53b7b95..8256edc 100644
--- a/tests/test_qwen_zimage_pipeline.py
+++ b/tests/test_qwen_zimage_pipeline.py
@@ -659,8 +659,7 @@ def test_no_face_path_still_runs_verified_text_restoration(monkeypatch):
     restore.assert_called_with(source, anchor, donor, manifest.lines)
 
 
-def test_tiled_verified_text_runs_vae_donor_per_tile(monkeypatch):
-    from remove_ai_watermarks._internal import qwen_zimage_pipeline, text_restoration
+def test_tiled_verified_text_is_rejected_before_model_work():
     from remove_ai_watermarks._internal.qwen_zimage_pipeline import QwenZImagePipeline
     from remove_ai_watermarks._internal.text_restoration import VerifiedTextLine, VerifiedTextManifest
 
@@ -668,12 +667,6 @@ def test_tiled_verified_text_runs_vae_donor_per_tile(monkeypatch):
     pipeline.device = "cuda"
     pipeline.progress_callback = None
     source = Image.new("RGB", (96, 80), (10, 20, 30))
-    restored = Image.new("RGB", (96, 80), (130, 140, 150))
-    pipeline._qwen_vae_roundtrip = MagicMock(side_effect=lambda tile: tile)
-    pipeline._run_global = MagicMock(side_effect=lambda tile, _strength, _seed: tile)
-    monkeypatch.setattr(qwen_zimage_pipeline, "detect_faces", lambda _image: [])
-    restore = MagicMock(return_value=restored)
-    monkeypatch.setattr(text_restoration, "restore_verified_text", restore)
     manifest = VerifiedTextManifest(
         "0" * 64,
         96,
@@ -681,23 +674,16 @@ def test_tiled_verified_text_runs_vae_donor_per_tile(monkeypatch):
         (VerifiedTextLine((4, 4, 20, 16), "Exact", "alphabetic"),),
     )
 
-    result = pipeline.run(
-        source,
-        strength=0.1,
-        seed=0,
-        tile=True,
-        tile_size=64,
-        tile_overlap=16,
-        text_manifest=manifest,
-    )
-
-    assert result is restored
-    assert pipeline._qwen_vae_roundtrip.call_count > 1
-    assert pipeline._run_global.call_count > 1
-    restore.assert_called_once()
-    assert restore.call_args.args[0].size == (96, 80)
-    assert restore.call_args.args[1].size == (96, 80)
-    assert restore.call_args.args[2].size == (96, 80)
+    with pytest.raises(ValueError, match="not calibrated with tiled diffusion"):
+        pipeline.run(
+            source,
+            strength=0.1,
+            seed=0,
+            tile=True,
+            tile_size=64,
+            tile_overlap=16,
+            text_manifest=manifest,
+        )
 
 
 def test_watermark_remover_dispatches_to_full_pipeline(tmp_path, monkeypatch):
@@ -757,6 +743,29 @@ def test_watermark_remover_dispatches_qwen_tiling_to_full_pipeline(tmp_path, mon
     assert output.exists()
 
 
+def test_watermark_remover_rejects_tiled_verified_text_before_pipeline(tmp_path, monkeypatch):
+    from remove_ai_watermarks._internal.text_restoration import VerifiedTextLine, VerifiedTextManifest
+    from remove_ai_watermarks._internal.watermark_remover import WatermarkRemover
+
+    _mock_watermark_runtime_deps(monkeypatch)
+    source = tmp_path / "source.png"
+    Image.new("RGB", (96, 80), (20, 30, 40)).save(source)
+    manifest = VerifiedTextManifest(
+        "0" * 64,
+        96,
+        80,
+        (VerifiedTextLine((4, 4, 20, 16), "Exact", "alphabetic"),),
+    )
+    remover = WatermarkRemover(device="cuda", pipeline="qwen-zimage")
+    runtime = MagicMock()
+    monkeypatch.setattr(remover, "_load_qwen_zimage_pipeline", lambda: runtime)
+
+    with pytest.raises(ValueError, match="not calibrated with tiled diffusion"):
+        remover.remove_watermark(source, text_manifest=manifest, tile=True)
+
+    runtime.run.assert_not_called()
+
+
 def test_qwen_tiling_runs_global_tiles_then_one_full_frame_face_stage(monkeypatch):
     from remove_ai_watermarks._internal.qwen_zimage_pipeline import (
         QwenZImagePipeline,
diff --git a/tests/test_script_help.py b/tests/test_script_help.py
new file mode 100644
index 0000000..c61b316
--- /dev/null
+++ b/tests/test_script_help.py
@@ -0,0 +1,32 @@
+"""Basic command-line contracts for standalone maintainer scripts."""
+
+from __future__ import annotations
+
+import subprocess
+import sys
+from pathlib import Path
+
+import pytest
+
+ROOT = Path(__file__).resolve().parents[1]
+
+
+@pytest.mark.parametrize(
+    "script",
+    [
+        "visible_groundtruth.py",
+        "visible_recall_sample.py",
+        "visible_sheets.py",
+    ],
+)
+def test_script_help_exits_cleanly(script: str) -> None:
+    result = subprocess.run(  # noqa: S603 -- fixed interpreter and repository-owned script path
+        [sys.executable, str(ROOT / "scripts" / script), "--help"],
+        cwd=ROOT,
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+
+    assert result.returncode == 0, result.stderr
+    assert "usage:" in result.stdout
diff --git a/tests/test_video_invisible.py b/tests/test_video_invisible.py
index 0f35223..235aca5 100644
--- a/tests/test_video_invisible.py
+++ b/tests/test_video_invisible.py
@@ -3,12 +3,14 @@
 from __future__ import annotations
 
 import csv
+import math
 import sys
 import threading
 from pathlib import Path
 from types import SimpleNamespace
-from typing import TYPE_CHECKING, cast
+from typing import TYPE_CHECKING, Any, cast
 
+import numpy as np
 import pytest
 
 from remove_ai_watermarks import optional_deps, video_encoding, video_invisible
@@ -92,6 +94,50 @@ def test_regeneration_rejects_noise_outside_unit_interval(tmp_path: Path) -> Non
         )
 
 
+@pytest.mark.parametrize(
+    ("kwargs", "message"),
+    [
+        ({"fps": 0.0}, "fps must be at least 1"),
+        ({"batch_size": 0}, "batch_size must be at least 1"),
+        ({"duration": 0.0}, "duration must be positive"),
+        ({"device": "tpu"}, "device must be auto, cuda, mps, or cpu"),
+    ],
+)
+def test_regeneration_rejects_invalid_controls_before_probing(
+    tmp_path: Path,
+    kwargs: dict[str, Any],
+    message: str,
+) -> None:
+    with pytest.raises(ValueError, match=message):
+        video_invisible.regenerate_video_candidate(
+            tmp_path / "source.mp4",
+            tmp_path / "candidate.mp4",
+            **kwargs,
+        )
+
+
+def test_fit_size_and_paired_psnr_validate_geometry() -> None:
+    assert video_invisible._fit_size(1920, 1080, 512) == (512, 288)
+    with pytest.raises(ValueError, match="positive"):
+        video_invisible._fit_size(0, 1080, 512)
+    with pytest.raises(ValueError, match="at least"):
+        video_invisible._fit_size(1920, 1080, 4)
+
+    frame = np.zeros((2, 2, 3), dtype=np.uint8)
+    assert video_invisible.paired_psnr(frame, frame) == math.inf
+    with pytest.raises(ValueError, match="matching shapes"):
+        video_invisible.paired_psnr(frame, frame[:1])
+
+
+def test_load_runtime_rejects_invalid_device_and_missing_extra(monkeypatch: pytest.MonkeyPatch) -> None:
+    with pytest.raises(ValueError, match="device must be"):
+        video_invisible.load_video_vae_runtime(device="tpu")
+
+    monkeypatch.setattr(video_invisible, "is_available", lambda: False)
+    with pytest.raises(RuntimeError, match="diffusion extra"):
+        video_invisible.load_video_vae_runtime()
+
+
 def test_encoder_and_mux_commands_separate_streaming_frames_from_source_audio(
     tmp_path: Path,
     monkeypatch: pytest.MonkeyPatch,
@@ -298,8 +344,9 @@ def test_shipped_defaults_match_a_certified_manifest_row() -> None:
     rate now fails here until a ``not_detected`` row exists for that exact triple.
 
     The tuple stops at three fields because the model is a fourth thing the oracle
-    was shown and neither tracked row records it. That omission is data-driven: add
-    ``vae`` here in the same commit as the first row that records one.
+    was shown and neither historical row recorded it. The manifest says
+    ``unrecorded`` rather than leaving an ambiguous empty field. Add ``vae`` here in
+    the same commit as the first row that records one.
     """
     with ORACLE_MANIFEST.open(newline="", encoding="utf-8") as stream:
         certified = {
@@ -320,6 +367,15 @@ def test_shipped_defaults_match_a_certified_manifest_row() -> None:
     )
 
 
+def test_oracle_manifest_marks_missing_vae_identity_explicitly() -> None:
+    with ORACLE_MANIFEST.open(newline="", encoding="utf-8") as stream:
+        rows = list(csv.DictReader(stream))
+
+    assert rows
+    assert all(row["vae"] for row in rows)
+    assert all(row["vae"] == "unrecorded" or "/" in row["vae"] for row in rows)
+
+
 def test_stream_batches_consumes_only_one_batch_ahead() -> None:
     consumed: list[int] = []
 
diff --git a/tests/test_watermark_registry.py b/tests/test_watermark_registry.py
index 53eddd3..c9f5e2b 100644
--- a/tests/test_watermark_registry.py
+++ b/tests/test_watermark_registry.py
@@ -529,7 +529,7 @@ class TestMarkKnowledgeIsOnTheRow:
 
     Product family, label regime, the platform sentence and the metadata signals that
     confirm the vendor all used to live in separate hand-maintained tables across
-    ``watermark_registry``, ``identify`` and ``api``. That is how LibLibAI ended up
+    ``watermark_registry``, ``identify`` and ``api``. That is how LiblibAI ended up
     registered but absent from the pill veto.
     """
 
@@ -563,7 +563,7 @@ class TestMarkKnowledgeIsOnTheRow:
 class TestPillSuppressors:
     """The pill veto is derived from the registry, not hand-listed.
 
-    The hand-written list drifted: LibLibAI was registered in the same commit as
+    The hand-written list drifted: LiblibAI was registered in the same commit as
     RunningHub and Baidu, both of which were added to the veto, and it was not. A
     derived set cannot be forgotten by the next registration.
     """
@@ -581,7 +581,7 @@ class TestPillSuppressors:
         assert not reg._keep_pill({"liblib"}, provenance=frozenset({"jimeng"}), footprint_flat=1.0)
 
     def test_pill_dropped_on_liblib_even_with_the_jimeng_wordmark(self):
-        """The veto precedes the wordmark arm, so a co-firing LibLibAI wins.
+        """The veto precedes the wordmark arm, so a co-firing LiblibAI wins.
 
         This is the broader half of the change: it needs neither TC260 provenance nor
         a flat footprint, so it is reachable on more inputs than the metadata arm.