Protocol
- Prepare rights-cleared scripts, storyboards, assets, voices, identities, pronunciation guides, captions, and channel requirements.
- Freeze product surface, model or mode, template, voice, prompts, settings, export format, edit allowance, and workstation or service environment.
- Retain scene versions, generated media, audio, captions, manual edits, failed renders, and reviewer interventions.
- Have factual, language, creative, rights, and accessibility reviewers score their assigned dimensions against the same timecoded master.
- Publish sample counts, duration, exclusions, per-scene failures, edit burden, disagreements, and inspectable evidence before any summary claim.
Planned measurements
- Script-meaning preservation
- Scene continuity and visual-defect rate
- Pronunciation and caption error rate
- Consent and provenance completeness
- Human edit and multimodal-review burden
Publication gate
The page remains preview and noindex until every gate is met.
- Script, identity, voice, and source-asset rights cleared
- Timecoded rubric locked before generation
- Every failed and regenerated scene retained
- Factual, locale, creative, and accessibility review recorded
- No showcase clip substituted for the declared sample
Why results are not publishable yet
These are real missing run artifacts and external review conditions—not completed evidence.
- No rights-cleared, reproducible script, storyboard, pronunciation, caption, and rights-cleared asset set with stable identifiers and expected-answer records has been published.
- No candidate run has frozen the product surface, model identifier, prompt, settings, tools, region, runtime, dependency versions, and hardware or service environment.
- No completed run log records sample size, exclusions, failures, interventions, start date, end date, and the exact configuration used for every candidate.
- No versioned scoring rubric and scoring implementation have been published with examples that another reviewer can reproduce.
- No blind or independent human-review record signed by factual, language, creative, rights, and accessibility reviewers has resolved disagreements and critical-failure labels.
- No inspectable input-to-output evidence bundle exposes failed, incomplete, excluded, and successful cases rather than only selected examples.
Sources checked
Open the original pages before relying on a time-sensitive product decision.