Evaluation and media provenance

Benchmarks, task datasets, attribution, metadata, interoperability and quality review

• articleWhere do the declared 1.0 meta fields (and the 0.x to 1.0 migration output) and the VRM Public License text read differently?
  VRM 1.0's meta.md defines commercialUsage values personalNonProfit (default), personalProfit and corporation, but the English VRM Public License 1.0 text uses only 'Non-commercial' and 'personal use' wording (no 'corporation' or 'personal profit'); UniVRM (efd20f62) migrates VRM 0.x commercial 'Allow' to personalProfit, never to corporation, writes the Japanese licence URL on export, and defines an English URL constant that returned 404.
• articleWhat OCIO and CLF test data are public at a pin, and what does the repository say about their licence?
  OpenColorIO (22dd9c4f) states that all data under tests/data/files (265 files, about 34 MB, including 7 ICC-named test files) is BSD-3-Clause, copyright OpenColorIO contributors, while THIRD-PARTY.md lists SampleICC under the ICC Software License 0.2 without mentioning the test data; the texts read do not say which governs the ICC test files.
• articleWhat exactly does Scott Enderle argue about Reagan et al.'s 'six basic emotional arcs', and what does his own notebook show?
  Scott Enderle's svd-noise notebook (repository MIT, commit a8cf6da3; self-described work in progress) argues that the shapes Reagan et al. report are what SVD produces from noise-like (Brownian) series, so fiction sentiment series may be best modelled as a kind of noise and research should move to more local questions; it does not claim plot structure is absent.
• articleHow are emotional arcs computed from text in Reagan et al. 2016, what do they not measure, and what do critics say?
  Reagan et al. (arXiv 1606.07772v3) build emotional arcs for 1,327 Project Gutenberg books by sliding 10,000-word windows scored with the labMT word list (Hedonometer) and decomposing them with SVD and clustering; they note dictionary methods do worse than random on single sentences and say the arc measures the emotional trajectory of the syuzhet, not the plot (fabula).
• articleWhat technical problems did a published critique find in the Syuzhet package, and what licence does the package carry?
  Annie Swafford's 2015 critique reports that the Syuzhet package merged sentences around dialogue in Bleak House and that one method produced NaN values on that text (author-reported); Syuzhet 1.0.7 (DESCRIPTION dated 2023-8-11, commit 73ec7d85) declares 'License: GPL-3' in DESCRIPTION, but the repository root has no LICENSE file and GitHub reports no licence.
• articleWhat do the BBC Editorial Guidelines and Ofcom's Fairness section require for reconstructions, factually based drama and archive material, and where do the two codes differ?
  BBC Editorial Guidelines 3.4.30 require reconstructions in factual programmes to avoid misleading over-dramatisation, rest normally on substantial verifiable evidence, be identifiable (labels or cues such as slow motion or grading) with obvious start and end, and generally not be staged for current-event news; 3.4.31 allows fictional characterisation and dialogue in factually based drama while expecting evidence-based portrayal. Ofcom's Section Seven (snapshot 16 Nov 2025) frames factually-based drama as a fairness obligation to individuals and organisations (7.9, 7.10) rather than a labelling rule.
• articleHow do Interop and SMPTE DCPs differ in practice, and what do libdcp's verifier (used by DCP-o-matic) and ClairMeta check?
  libdcp's verifier (891facc8) has a BV21_ERROR level for Bv2.1 'shall' violations, flags Interop DCPs (INVALID_STANDARD, Bv2.1 s.6.1) and mixed standards, warns above 52 and errors above 79 characters per subtitle line, errors above 32 characters per closed-caption line and above 3 lines, and checks JPEG 2000 code-block size of 32; ClairMeta (b3b66a02) settings use 250 Mb/s for DCI, 500 for HFR and 400 for DVI, with a comment noting asdcplib's 400 Mb/s HFR threshold.
• articleWhat does YuE's MODEL_LICENSE (YuE2) say clause by clause about hosting, redistribution, modification, training and output use of the weights, and what do THIRD_PARTY_NOTICES add?
  At YuE 1647252d, MODEL_LICENSE licenses the three YuE2 checkpoints under CC BY-NC 4.0 with a dated (2026-09-16) additional permission for individual creators to generate and monetise outputs under responsible-use conditions; it excludes code/tokenizer/evaluation assets from its scope, denies commercial redistribution or sale of weights, and directs companies to a commercial licence. This fills the MODEL_LICENSE gap recorded by L07 for C2-B04-H-12.
• articleIs YouTube Audio Library music safe from Content ID claims, and what attribution does it require?
  Problem: choose background music for a YouTube video without claims. Conditions: tracks and effects from YouTube Studio's Audio Library (help page fetched 23 Oct 2026). Method: Audio Library items are described as royalty-free production music and sound effects that are copyright-safe: tracks downloaded from it will not be claimed by a rights holder through Content ID, and Partner Program channels can monetise videos that use them. Attribution: if a track has a Creative Commons licence, you must credit the artist in the video description (Studio generates the text; filter 'Attribution required' / 'Attribution not required'); videos with Audio Library music show a 'Music in this Video' section, and CC attribution is still required in the description. Limits: only Audio Library items are known to YouTube to be copyright-safe; YouTube is not responsible for issues with 'royalty-free' music from channels or other libraries; it cannot give legal guidance; the library is only in YouTube S...
• articleWhat does YouTube's Studio Trends tab show (top searches, breakout videos, content gaps for Shorts) and how does it define a content gap and audience interest?
  Problem: choosing topics from demand rather than guesswork. Conditions: YouTube Studio > Analytics > Trends; some insights limited by country, language and device; the page notes an updated Studio experience rolling out from July 2026. Method (documented): enter a topic or browse the trending page and save search terms. Cards: top searches (your audience and your saves, 28 days), breakout videos (well-performing content from similar creators), recent videos (topics your audience watched in the last 28 days plus saved searches) and content gaps for Shorts. A content gap is when viewers cannot find enough quality search results for a query: no results, no exact match, or old/low-quality results. Audience interest ranges from very low to very high and is based on videos watched over 1,000 times per week in the last 28 days. Failure modes: treating a gap as proof of demand; missing sections when no relevant videos exist. Limitations: documentation only; no evidence that acting on gaps i...
• articleHow does YouTube define audience retention and its "key moments" (intro, top moments, spikes, dips), and what does YouTube say to change about a video opening?
  YouTube Help (undated page, captured 2026-10-23): the key-moments report is video-level only and takes 1-2 days to process. Intro = percentage of viewers still watching after the first 30 seconds; YouTube reads a high intro as the opening matching the thumbnail/title promise, and recommends either changing thumbnail/title to reflect the content or modifying and experimenting with the first 30 seconds. Top moments = almost no drop-off (move such content earlier because audiences shrink over time). Spikes = rewatched or shared sections, which can also mean unclear content. Dips = skipped or abandoned sections. Moments only show for videos of at least 60 seconds with at least 100 views; "typical retention" compares the 10 latest videos of similar length; retention can be segmented by new vs returning viewers, subscribers vs not, and organic vs paid. Note YouTube treats packaging and opening as one promise: low intro retention may be a title/thumbnail mismatch, not a weak hook.
• articleHow does YouTube's title/thumbnail A/B test (Test & compare) work: variants, winning metric, eligibility, limits?
  Per YouTube Help (captured 2026-10-23): test up to 3 titles, thumbnails, or title+thumbnail pairs; desktop Studio only, advanced features required; not available for Shorts, scheduled lives or premieres (premieres after conversion and live archives are allowed), nor made-for-kids, mature or private videos. Changing title/thumbnail mid-test stops it; tests take a few days to 2 weeks. Outcomes are Winner, Performed Same or Inconclusive, judged on watch time share (not CTR) with concurrent A/B/C delivery and a small held-out control group; with no clear winner the first-uploaded option is kept. Thumbnails below 1280x720 force all variants to 480p. YouTube warns that sequential third-party testers often optimise CTR and can pick different winners, and recommends starting with older videos and testing clearly different variants.
• articleHow does YouTube define impressions, impressions CTR, RPM vs CPM, and where are impressions counted?
  YouTube Help (captured 2026-10-23): an impression counts when a thumbnail is shown for more than 1 second with at least 50% visible, only on YouTube surfaces (not external sites/embeds, end screens etc.); impressions CTR is computed only from views that came from counted impressions, so views/impressions will not equal CTR; YouTube states half of channels/videos fall between 2% and 10% CTR. RPM = total revenue after YouTube's share per 1,000 views, including memberships, Premium, Super Chat and Super Stickers, and the page says RPM is calculated per 1,000 engaged views for Shorts and all views for long-form videos; CPM = advertiser cost per 1,000 ad impressions before revenue share, so RPM is lower (after share and including unmonetized views). New viewers = first time watching the channel in the period; returning = watched before. A standalone "unique viewers" definition page was not retrieved in this batch (answer/9314419 and 9314422 returned a generic shell): gap.
• articleWhat does YouTube's Inspiration tab offer (hooks, outlines, titles, thumbnails), when is it being deprecated, and what are its AI, provenance and data-use caveats?
  Problem: using YouTube's own AI ideation inside Studio. Conditions: Studio on desktop, English only, access varies; the page says that from August 2026 the Inspiration tab is gradually deprecated and creators should use Ask Studio for brainstorming. Method (documented): open Content > Get inspired; the tab shows nine suggested ideas from your channel data; refine by prompt or chips, base ideas on past videos, 'More like this', bookmark. Each idea card has a summary, image, audience-interest indicators, aggregated comment insights, prediction signals, channel alignment and related recent videos; selecting an idea gives an outline, title and thumbnail suggestion, with card types: Hooks (opening-segment ideas), Outlines, Titles, Thumbnails, Related videos. Provenance: generated thumbnails may carry a signed C2PA manifest which downstream platforms can read. Data: prompts connected with your channel are deleted automatically after 45 days; human reviewers may read conversations after di...
• articleWhat does YouTube say about the Shorts revenue-sharing threshold from Feb 2027, the Premium revenue pools and the promised new incentive programs?
  Problem: planning Shorts-based income. Source: YouTube Official Blog, 10 Aug 2026 (primary). Source statements: from 1 Feb 2027, creators with 10 million qualified Shorts views over the last 90 days are eligible for ads and subscription revenue sharing on Shorts; channels below stay in YPP and keep earning on long-form content, and Shorts revenue sharing resumes automatically after they cross 10 million again. For channels under the threshold YouTube promises new incentive programs (bonuses for YouTube Shopping, incentives for brand deals, earnings boosts for starting and growing trends) with 'more details soon'; no amounts or criteria were published in the post. Premium: revenue pools of 30% of net subscription revenue for Premium and 60% for Premium Lite, distributed on member watch time and views, then creator revenue share 55% long-form and 45% Shorts; Premium Lite expands to all Premium countries. The post claims YouTube expects to pay more to creators in 2027 than in 2026 and ...
• articleHow do S3 versioning and Object Lock compare with Cloudflare R2 bucket locks for making generated assets immutable, and what is missing on R2?
  Problem. Making finished renders and their sidecars tamper-resistant for provenance or rights disputes. Conditions. Amazon S3 User Guide (Versioning, Object Lock) and Cloudflare R2 docs (bucket locks updated Oct 20, 2026; S3 API page Oct 14, 2026). Method. S3 versioning is off by default; once enabled an overwrite creates a new version and a delete inserts a delete marker, so earlier versions are recoverable. Object Lock works only in buckets with versioning enabled; in compliance mode a protected object version cannot be overwritten or deleted by any user including the root user and retention cannot be shortened, while governance mode allows privileged bypass (docs describe both). Lock-protected objects also disallow annotation changes; to annotate, create a new version. R2's S3 compatibility table marks GetBucketVersioning and PutBucketVersioning as not implemented; instead R2 bucket locks prevent deletion and overwriting for a period or indefinitely via per-prefix rules (an examp...
• articleWhat do the Audience tab's 'Channels that your audience watches' and 'What your audience watches' reports show, over what window, and what are their documented uses?
  Problem: knowing what else your viewers watch. Source: YouTube Help 'Understand your YouTube audience' and 'Tips to learn what viewers are watching'. Source statements: the Audience tab shows monthly audience (unique viewers over the previous 28 days, recalculated daily) split into new, casual and regular viewers. 'Channels that your audience watches' shows other channels your viewers consistently watched outside your channel over the past 28 days, for interests and collaboration; 'What your audience watches' shows other videos, Shorts, live streams and podcasts watched outside your channel over the past seven days, for topics, titles, thumbnail ideas and collaborations; 'Formats your viewers watch' covers videos, Shorts and live in the last 28 days. Official Artist Channel owners do not see videos where they are the primary artist. The Tips page suggests looking for patterns, themes in titles and thumbnails, and collaboration opportunities. Limits stated: some data (geography, traf...
• articleWhat do the InsightFace repositories say about the licence of buffalo_l, antelopev2 and other pretrained models versus the MIT-licensed library, and who must be contacted for commercial use?
  Problem. IPAdapter FaceID, face swap and portrait nodes in ComfyUI depend on insightface models. Conditions. deepinsight/insightface commit c6c3af7b (2026-10-19). Cross-checks an earlier round's licence item without repeating it. Method. The main README states the code is MIT with no limit on academic or commercial use, but training data with annotations 'and the models trained with these data' are for non-commercial research only, and this applies both to manual downloads and to auto-downloads through the Python library. It lists contacts for licensing: inswapper-series face swap models (inswapper_128.onnx etc.), the open-sourced face recognition packages such as buffalo_l (a separate recognition-oss-pack contact), and the InspireFace SDK. The model_zoo README opens with 'ALL models are available for non-commercial research purposes only'; the python-package README repeats that the pretrained models are non-commercial research only, whether downloaded automatically or manually, and...
• articleHow do I store generated media under content-addressed (sha256) keys without overwriting or racing, using S3 or R2 conditional writes and checksums?
  Problem. Deduplicating and verifying generated assets across retries (see Celery at-least-once finding). Conditions. Amazon S3 User Guide (conditional writes, checking object integrity) and Cloudflare R2 S3-compatibility docs (page updated Oct 14, 2026). Method. Name the object key after the content hash (for example outputs/sha256/ab/abcd...); upload with If-None-Match: * so the write succeeds only if the key does not exist (S3: header prevents overwrites by validating no object with that key; requires SigV4). R2 documents that conditional headers on PutObject are evaluated atomically at commit, and that with concurrent If-None-Match: * on an absent key at most one write succeeds and the others get 412 PreconditionFailed; treat 412 as 'already stored'. S3 can verify uploads with checksums; supported algorithms include SHA-256 (CRC64NVME is the default algorithm for S3 checksum calculation), so send the SHA-256 you computed and let the service reject corrupt uploads (S3-specific; th...
• articleWhat are 'content gaps' in YouTube Studio's Trends tab (formerly Research), what data window and limits apply, and how should an agent use them?
  Problem: choosing topics from search demand. Source: YouTube Help 'Explore trends on YouTube' (the page that earlier documented the Research tab; the word 'Research' does not appear on the page as fetched, and the Studio path is Analytics, Trends tab). Source statements: Top searches shows searches from your audience and your saves over the last 28 days; Breakout videos highlights well-performing content from similar creators; 'Content gaps for Shorts' lists Shorts-related search terms tied to topics your audience watched in the last 28 days. A content gap is when viewers cannot find enough quality results for a search: no results, no exact match, or no relevant videos (for example content that is old or low quality). Audience interest, from very low to very high, is based on videos watched over 1,000 times per week in the last 28 days. Some insights are limited by country, language and device, and some sections can be empty. Method (inference, labelled): list gap terms, check the t...
• articleFor a ComfyUI video/image stack, how do code, weights and outputs line up across Wan, Hunyuan, FramePack, LTX, AnimateDiff, RIFE and InsightFace, and which limits are territory, scale, revenue or competing-model clauses?
  Problem. One-glance triage before shipping a workflow or hosted service. Conditions. Synthesis of the sibling findings (pinned revisions in each); not a legal opinion; each cell restates what the cited text says. Method (matrix: code / weights / outputs / hard limits / duties). Wan 2.1/2.2/Animate: Apache-2.0 / Apache-2.0 / no claim by licensor, user accountable / none found / Apache notice duties. HunyuanVideo: licence terms in Tencent Hunyuan Community License / same / Outputs may not be used to improve other AI models, none claimed over content ownership beyond that / excluded territory EU, UK, South Korea; 100M MAU gate; Hosted Service counts / give recipients the agreement, Notice file, change notices, downstream use restrictions. FramePack: Apache-2.0 code / unspecified in sources / unspecified / possible Hunyuan inheritance (unresolved) / none stated. LTX-2 and LTX-2.x: community licences / same / outputs: LTX-Video 0.X says no rights claimed; 2.x text defines Output and bars...
• articleHow do I run a fair content experiment with YouTube Studio's own tools, which variables to fix, how long, and why views alone cannot show cause?
  Problem: deciding whether a change (hook, length, format, thumbnail) helps. Documentation (source_statement): YouTube's Tips page says to compare videos of the same format because audience behaviour differs across formats, and to group similar videos in Analytics and compare them in the watch-time report; the Audience page defines monthly audience as a rolling 28-day window and shows rolling windows of 7 and 28 days for other reports. The native thumbnail/title test (Test & Compare) is described in C3-B573-04. Method (inference by this worker, not a YouTube instruction): (1) write the hypothesis and one primary metric (for example average view duration or relative retention at 30 s, not raw views) before publishing; (2) change one variable and hold topic, format (Shorts vs long-form), length band, publish slot, title/thumbnail pattern and upload cadence constant; (3) publish at least several matched videos per arm, or use Test & Compare where it applies, rather than one video each; ...
• articleWhat do YouTube's comment settings do (Basic/Strict/Hold all, blocked words, link blocking, hidden and approved users, subscriber-only commenting), and what changes for viewers?
  Problem: setting up moderation for a channel. Source: YouTube Help 'Learn about comment settings'. Source statements: per-video comment settings are On, Pause or Off. When On, Comment moderation options are None, Basic (hold potentially inappropriate comments), Strict (a broader range) and Hold all; held comments are kept in Studio for up to 60 days, are not public unless approved, and are available for review in over 100 languages. Comments can be limited to subscribers and paid members, with a minimum subscription time (any duration, 1 hour, 1 day, 1 week); this is not available at channel level. Channel-level: hidden users (their comments are hidden across all videos; they also cannot create clips), approved users (comments published automatically and not filtered for blocked links, words or inappropriate content), blocked words (comments containing or closely matching them may be held up to 60 days; live chat messages with them are blocked), blocked comments with links (links he...
• articleWhat usage terms, consent and disclosure duties do the so-vits-svc README and RVC repo state, and how do their licences differ?
  Problem. Open voice-changer tools are widely used on real people's voices; an agent must know what the maintainers do and do not say. Conditions. so-vits-svc 4.1-Stable README; RVC WebUI README and LICENSE. Method. so-vits-svc: states the original purpose was fictional anime characters and that anything involving real individuals deviates from it; says the project is for academic use and not for production deployment; makes users solely responsible for dataset authorisation and for infringement from input sources; requires that videos posted to platforms state the input vocals/audio source (link the original or say it is your own or synthesised); bars illegal, religious and political use; reproduces Chinese Civil Code provisions, including the clause that voice protection applies by reference to portrait-right rules. Licence: AGPL-3.0 (header read). RVC: MIT licence (copyright holders listed); the README text I fetched contains no consent or misuse clause (inference from search; I d...
• articleWhat rights does the NO FAKES Act of 2025 (H.R. 2794 as introduced) create for voice and likeness, and how do licences, minors and union contracts work? (bill, not law)
  Corrected 2026-10-23 - see C3-B614-14; the original statements below are kept for history and are superseded where the correction says so. Problem: understand what a proposed US federal digital-replica right would require of producers and performers. Status: an introduced bill (119th Congress, 9 April 2025); not law as of this text, and the introduced text may have changed. Method (source text): it defines a digital replica as a newly created, computer-generated, highly realistic representation readily identifiable as a person's voice or visual likeness, either in work they did not perform or in a version whose performance was materially altered; it makes the authorisation right a licensable property right that is not assignable during life; post-mortem it lasts 10 years for the right holder plus 5-year renewals on proof of active use, ending no later than 70 years after death. Licence rules: a living adult's licence is valid only up to 10 years, must be written and signed, and must...
• articleUnder the NO FAKES bill text, who is liable for unauthorised voice replicas, what are the exclusions, and what takedown and damages mechanics apply? (bill, not law)
  Corrected 2026-10-23 - see C3-B614-14 and C3-B614-15; the original statements below are kept for history and are superseded where the correction says so. Problem: assess exposure for generating or hosting a voice clone. Status: introduced bill, not law. Method (source text): liability attaches to publicly displaying, distributing or making available an unauthorised digital replica, and to distributing a product or service primarily designed to produce unauthorised replicas of an identified person, limited-use for that, or marketed for it. Knowledge: an online service is liable only after receiving a compliant notice or court order (or wilfully avoiding one); others need actual knowledge or wilful avoidance. Exclusions: bona fide news or sports broadcasts, documentary or biographical depiction (not if it falsely suggests authenticity, and not for synchronised music recordings except where First Amendment protected), commentary, criticism, scholarship, satire or parody, fleeting or ne...
• articleFrom TikTok Business Help (R1-R4): Symphony Creative Studio is a free AI video tool for TikTok-optimised organic and paid content: text/image/reference-to-video generation, image generation, voiceover avatars (choose from a library filtered by industry, gender, background, region; avatars...
  Corrected 2026-10-23 - see C3-B613-05 and C3-B622-05; the original statements below are kept for history and are superseded where the correction says so. From TikTok Business Help (R1-R4): Symphony Creative Studio is a free AI video tool for TikTok-optimised organic and paid content: text/image/reference-to-video generation, image generation, voiceover avatars (choose from a library filtered by industry, gender, background, region; avatars labelled "Real-human or AI-generated"), product avatars (upload a product or app-screen image and get clips of an avatar holding or modelling it; clothing accessories such as shoes, hats, sunglasses are not supported), translate-and-dub with optional lip sync and captions, an editor, and "Symphony Agent" that turns a prompt into a storyboard and full video. Dreamina Seedance (R2): ByteDance video models integrated into Symphony in variants - Standard (default; broadest features incl. Agent, reference/image/text-to-video and Avatar), Fast (speed; A...
• articleWhat does YouTube's own TV guidance say creators should do for living-room viewing (device filter, 4K, thumbnails, channel art, episodic playlists, pacing, audio checks), and what is data versus advice?
  Problem: optimising for TV. Sources: YouTube Blog posts 'Maximize your reach: 5 tips for YouTube success on TV' (Nov 2024, product manager for connected TV) and 'Creators are taking over TV: 10 tips' (Apr 2025, based on a creator discussion). I found no dedicated YouTube Help page on TV for creators; the end-screens (6388789) and chapters (9884579) Help pages, fetched this round, contain no TV-specific text, and Shorts-on-TV appears only in news coverage, so these are blog posts, not documentation. Platform statements (self-reported, undated data): over a billion hours of YouTube are watched on TVs daily; viewers tend to watch longer sessions on TV; in Analytics Advanced mode filter by Device type to see TV watch time and views; one can also track new subscribers from TV; upload in 4K; thumbnails are supersized on TV, so use 1280x720 or higher, clean and readable; channel banner 2560x1440, 6 MB max, simple and legible from afar; episodic series in playlists with a consistent title f...
• articleWhat are Seed-VC's practical inputs, latency, singing mode and consent-relevant switches, and under what licence is it released?
  Problem. Choosing an open voice converter for a pipeline requires knowing input limits, real-time latency, singing handling and licence. Conditions. Seed-VC main branch README. Method. Reference speech of 1 to 30 seconds clones a voice with no training; optional fine-tuning needs as little as one utterance per speaker (1 to 30 s files, clean, no background music or noise). Real-time mode has stated algorithm delay about 300 ms plus about 100 ms device delay. Singing: set f0-condition to True and use 30 to 50 diffusion steps; auto-f0-adjust is normally off for singing; semi-tone-shift transposes. A v2 option convert-style uses an autoregressive model to convert accent and emotion (false gives timbre-only conversion); anonymization-only ignores the reference and maps speech to an average voice. Failure modes. Noisy or music-laden source or training audio is explicitly undesirable. Limits. Repo README claims, not independently run. Rights. The repo LICENSE is GNU GPL v3 (copyleft; I re...
• articleWhat new TV features did YouTube announce in Oct 2025 (50 MB thumbnails, AI super-resolution upscaling with opt-out, contextual search, shopping QR), and how does the Help page now match?
  Problem: understanding platform-side changes to how videos appear on TV. Source: YouTube Blog 'New features to help creators shine on TV screens' (Kurt Wilms, 29 Oct 2025), compared with the live thumbnails Help page. Platform statements: channels earning six figures or more from TV screens rose by over 45% (July 2024-June 2025 vs prior year; YouTube-reported); the thumbnail file limit would 'soon' expand from 2 MB to 50 MB so YouTube can serve 4K thumbnails (the Help page now lists a 50 MB desktop limit and 2 MB on mobile, so this has at least partly happened as of 2026-10-23); a new AI-powered feature generates higher resolutions, starting by upscaling videos uploaded below 1080p from SD to HD, with a goal of up to 4K; original files and resolutions are kept, there is an opt-out, and viewers can watch the original resolution, with 'super resolution' labelled under settings; channel pages get immersive previews, and Shows design groups videos; contextual search on TV prioritises a ...
• articleDid Illinois HB4875 become law, and when does it take effect?
  Problem. The earlier note on enrolled HB4875 left enactment and effective date unverified. Method. The Illinois General Assembly bill-status file for HB4875 (103rd GA) shows Governor Approved on 8/9/2024, Effective Date January 1, 2025, and Public Act 103-0836. So the digital-replica amendments to the Right of Publicity Act are in force; the enrolled text previously summarised applies subject to any later amendment I did not check. Use: treat Illinois consent and platform-liability rules as live for uses in Illinois from 1 January 2025. Failure modes: assuming a bill status page equals text in force; later 104th GA amendments were not checked (the HB4875 number in the 104th GA is an unrelated procurement bill). Limitations. Status file only; I did not re-read the Public Act text or the statute as codified. Version/date. Fetched 2026-10-23. Ledger: Tennessee HB2091 (ELVIS Act) page shows signed 03/21/2024, Public Chapter 588, effective 07/01/2024, matching earlier items.
• articleWhat changed in the 2026 NO FAKES text: counter-notification, post-mortem registration, and what stayed the same?
  Problem. Notes on H.R. 2794 (2025 IH) omit a user-side process. Method. Reported S. 4591 text: after a compliant counter-notification a provider that opts to restore material must send the complainant a copy and restore not less than 14 days later, unless an eligible plaintiff sues, in which case the material stays down; false notices and counter-notices carry penalties. The post-mortem right runs 10 years with renewal on proof of active use (a 5-year period appears in the termination clause), capped at 70 years after death, and renewal must be filed with the Register of Copyrights, who keeps a public directory. Per-work damages tiers of $5,000, $25,000 and $750,000 remain in the text. A living-person licence is valid up to 10 years and a minor's licence is capped at 5 years, with collective-bargaining agreements treated separately, as before. Use: for takedown and platform design, model the 14-day restore window. Failure modes: assuming a one-way takedown. Limitations. I compared t...
• articleCan an AI-assembled "faceless" documentary channel monetize on YouTube, and what does YouTube policy say about template/AI mass production?
  YouTube's channel monetization policies (page as served 23 Oct 2026) renamed the 'repetitious content' policy to 'inauthentic content' in a notice dated 15 July 2025, clarifying that it covers repetitive or mass-produced content. The policy lists as an example 'AI-generated content made with generic or unoriginal templates giving the impression of mass production without adding the creator’s original, authentic insights or perspective', and says that when automated tools or templates help create content, the final product must still demonstrate the creator's creative vision and provide educational or entertainment value. YouTube applies these policies when it checks whether a channel is suitable to monetize; copyright is a separate policy. A sponsored YouTube tutorial (19 Sep 2026) demonstrates a one-click 'faceless documentary' tool that drafts a script with an LLM, adds a stock text-to-speech voice, stock footage, auto-thumbnail and captions; according to discovery's reading of th...
• articleWhat does YouTube itself advise for titles and thumbnails, how should their effect be measured, and what thumbnails are disallowed?
  YouTube Help (captured 2026-10-23): "90% of the best-performing videos have custom thumbnails" (YouTube statistic, no method given). Thumbnail advice: design for the target audience (familiar faces for subscribers; universal actions/emotions for casual viewers), rule of thirds, branding and readable text, avoid over-complex designs, make images large because display varies by device, keep current with community styles and experiment by updating older thumbnails. Titles: be accurate (inaccuracy causes viewers to stop watching and can hurt discoverability), succinct with key words first and branding/episode numbers last, limit ALL CAPS and emoji; choose searchable vs intriguing titles by intent. Measurement: for general audiences check impressions CTR on Home and Suggested in the first 24 hours on videos with above-average impressions; for subscribers check CTR in the Subscriptions feed in the first 24 hours; use research insights and the Audience tab for ideas. Policy: thumbnails vio...
• articleIs the NO FAKES Act law, and which bill number and stage is current (versus the H.R. 2794 text already in the notes)?
  Problem. Earlier notes describe H.R. 2794 (2025, introduced). Status check. Primary text on GPO shows the 119th Congress 2nd session bills S. 4591 and H.R. 8915 introduced 20 May 2026 as the NO FAKES Act of 2026; S. 4591 was reported by Mr. Grassley with an amendment (a substitute) on 24 June 2026 and sits on the Senate Calendar as No. 446. No enactment appears in the sources I could fetch; a Daily Journal headline found only through search says a Senate unanimous-consent request was objected to (not read). Method. For any statement about NO FAKES, cite S. 4591 (RS) rather than H.R. 2794 IH; effective date in the reported text is 180 days after enactment. The Recording Academy page lists 'S. 1367/H.R. 8915' for the bill, which mixes the 2025 Senate number with the 2026 House number, so confirm numbers from GPO. Failure modes: quoting 2025 introduced text as current. Limitations. I could not reach congress.gov (no status page) or the Daily Journal body, so the floor status after 24 J...
• articleIn the FTC Endorsement Guides (16 CFR 255), where is the example about relying only on a platform's built-in disclosure tool? Correction to C3-B500-01: it is Example 9(iii) under section 255.0(g), not section 255.5 Example 9 (which is a points-for-prizes programme).
  Problem. C3-B500-01 attributes the platform-disclosure-tool worked example to 's255.5 example 9'. Conditions. Anyone citing the Guides for creator or AI-avatar ads. Method. In the current eCFR text the relevant example is in section 255.0(g) (Examples), Example 9: (i) disclosure only on profile pages is not clear and conspicuous; (ii) disclosure behind a link labelled 'more' is not unavoidable; (iii) relying solely on a platform's built-in tool fails where the disclosure is small, low-contrast, competes with overlaid text and appears for five seconds. The paid game-play live-stream example (C3-B500-01's 'example 8') is also section 255.0(g) Example 8. Section 255.5 Example 9 is a different scenario (points awarded for social posts, redeemable for prizes). Failure modes. Citing 255.5 for the platform-tool point sends a reader to the wrong example. Limitations. The substance of C3-B500-01's claim is supported; only the locator is wrong. Version and date. eCFR current text last amended...
• articleWhat does a "copy a viral Short's structure" AI Shorts workflow look like, and what policy risks does it carry?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Youri van Hofwegen (2026-07-09, OpenArt affiliate): find a high-view Short in any niche, pull its transcript (third-party transcript site), ask Claude to rewrite a new script for your niche "in the same style, length, and tone", generate an ElevenLabs v3 voice-over (filter voices by accent/gender/"conversational"), have Claude write image prompts tailored to the target image model (GPT Image 2, 1:1, high quality) for meme stills, lay them over muted "copyright-free" gameplay footage in CapCut with auto-captions. He claims ">90%" of beginners get under 1,000 views because they chase originality, unsourced. Risks under YouTube rules: templated, mass-produced or near-ident...
• articleWhat is the difference between TikTok's Commercial Music Library and the general library for business accounts, and what limits apply?
  Problem: a brand or business account wants to use music in TikTok content. Conditions: TikTok Business Help (updated July 2025) and Commercial Music Library user terms (fetched 23 Oct 2026). Method: the CML is a pre-cleared library (the help page says 1 million songs) for businesses. Businesses cannot use the general music library for commercial usage and should use the CML for all commercial TikTok activities: organic content (including duets, reacts and stitches with user videos), video ads and branded content. Original sounds from other users or other licensed sounds require your own licence check with legal counsel. The terms add: Commercial Uses outside TikTok are not permitted and no rights are granted for them (separate licensing needed); Commercial Sounds are the only sounds made available for Commercial Uses; 'Premium' tracks may carry an additional fee; if TikTok loses the right to a sound it may take down videos or mute the audio; you are responsible for claims arising fr...
• articleIn ComfyUI workflow JSON, what does the top-level 'version' field mean, and which fields actually record the frontend and node-pack versions?
  Problem. People read workflow 'version' as an application version and then cannot explain why a workflow made on one frontend misbehaves on another. Conditions. Comfy-Org/ComfyUI_frontend commit 174bd880 (package.json version 1.59.0), workflowSchema.ts and src/scripts/app.ts. UI-format workflows only (API-format prompts have no such field). Method. (1) The validator reads only a numeric 'version'; if it equals 1 it applies the schema-version-1 definition, and anything else is validated as the older 0.4 schema. So 'version' is a graph-schema number, not a ComfyUI or frontend release. (2) The frontend release that saved the file is recorded separately as extra.frontendVersion (optional string). (3) Each node can carry properties.cnr_id (registry id), properties.aux_id (github user/repo for non-registry packs) and properties.ver, which must be a semantic version, a git commit hash or 'unknown'. (4) Optional models arrays at graph or node level list model files (see C3-B574-09 for hashe...
• articleWhat output resolutions, edit/extend limits and provenance marks does Google's Gemini Omni Flash video documentation state, and what is 'upscaled' there?
  Problem. A pipeline needs to know which dimensions are native, what edits are possible, and what marks the output carries. Conditions. Gemini API Omni documentation (raw markdown) fetched 2026-10-23; the sibling video page says Veo 3.1 Preview in the Gemini API was shut down on October 22, 2026 and points to Omni (gemini-omni-1.1-flash) or GA Veo via the Gemini Enterprise Agent Platform. Method (documented). aspect_ratio supports 9:16 and 16:9; resolution values 360p, 720p (default), 1080p and 4k, where the table labels 1080p and 4k as upscaled outputs; image-to-video, first and last frame interpolation, subject reference images and stateful conversational editing exist. Limitations list: editing or extending uploaded videos is unavailable in the EEA, Switzerland and the UK (model-generated videos can still be edited); uploaded inputs for editing/extension must be 10 s or less; extension only appends at the end; no extension of an uploaded video where someone talks to add dialogue; ...
• articleAre AI thumbnail "scores" (virality/clarity/curiosity/emotion) a substitute for YouTube's own title/thumbnail testing?
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. In a Pixels-sponsored demo (2026-08-23) an AI thumbnail tool generates thumbnails from short prompts, "recreates" proven thumbnail layouts with a new subject or a trained face persona, and scores thumbnails 0-100 on virality, clarity, idea, curiosity and emotion, reading title and thumbnail together; a "one-click fix" rebuilt two of his underperforming thumbnails from 44 and 33 to 99 and ~100. Useful design heuristics he states: get the message across at phone size within seconds; create a curiosity gap (show the verdict, hide the reason; opposite halves such as mask vs face); state rather than ask; an image that looks like it is happening now beats a concept; clarity w...
• articleWhat happens when a video gets a Content ID music claim on YouTube (block, monetise, track), and how long do dispute and appeal take?
  Problem: a published video gets a copyright claim for its music. Conditions: YouTube Content ID claims (not strikes); help pages fetched 23 Oct 2026. Method: a claim can be generated when an upload matches a rights-holder reference. Claimants choose a policy: monetise (most common for music), track, or block; policies can differ by country. For videos over three minutes, tracked or monetised videos stay up with the claim. For Shorts of 1-3 minutes, an active claim blocks the video regardless of policy and there is no strike for videos with active claims. Claims affect videos, not usually the channel. Options: leave it, remove or replace the claimed part, or dispute if you have the rights, a copyright exception, or believe it was an error. Dispute: the claimant has 30 days to respond; they can release the claim, reinstate it, submit a copyright removal request (which can lead to removal and a strike) or let it expire. If reinstated you may appeal; the claimant then has 7 days; 'Escal...
• articleBudgeting an AI short film: the "$200 in two days" plan re-checked against Oct-2026 prices
  MindStudio's March-2026 post plans a 2-3 minute film in two days: Claude (Projects to keep script, shot list, style guide and character descriptions loaded) for treatment and structured prompts, Seedance 2.0 for clips, Luma Dream Machine Canvas for assembly (DaVinci Resolve for finishing), ElevenLabs for VO, Suno/Udio for music; budget table $143-$195; plan a 4:1 shooting ratio (about 100 attempts for 25 used clips); write a one-page treatment first and tell the LLM to keep it "achievable with AI-generated footage". Currency problems: it states Seedance 2.0 makes "up to 10-second clips" and that a 10 s 1080p clip costs "roughly $0.80-$1.20"; later sources show 15 s clips (C3-B393-02) and Runway's API lists Seedance 2.0 at 40 credits/s at 1080p ($4.00 per 10 s; C3-B387-01) - host prices vary widely, so the $200 total should be recomputed per host before reuse. At Runway API rates, 100 x 10 s 1080p attempts would be ~$400 for Seedance 2.0, ~$680 for Seedance 2.5, or ~$240 for FLUX 3 f...
• articleWhat does Instagram officially say helps or hurts Reels reach (originality, watermarks, length, first seconds, trial reels), and how does that differ from YouTube?
  Instagram official pages (captured 2026-10-23): reels follow the Recommendation Guidelines and are made less visible to non-followers if low-resolution, watermarked, muted, bordered, majority text, or already posted on Instagram (reposts); clickbait, engagement bait and contest/giveaway promotion are non-recommendable; Instagram says its most important predictions for reels include how likely you are to reshare a reel and to watch it, and it surveys users ("is this worth your time?"). Creator FAQ tips: upload the highest resolution, make the first 3 seconds engaging, ditch third-party watermarks (e.g. from other apps), post original content; reels over 3 minutes are not recommended to unconnected audiences. Jan 2025 update: US creators could publish reels up to 3 minutes; "Trial reels" show content only to non-followers first; Edits app announced; ranking changes aimed at giving creators of all sizes a chance. Platform differences: unlike YouTube (A/B tests by watch time, C3-B336-02...
• articleDo platforms actually label AI content? A 2026 audit: only 61% of provenance-tagged AI uploads got labels, and platforms often strip the provenance data
  Measured evidence (abstract level). A legally grounded audit across Instagram, TikTok, X and YouTube using the European Commission's July 2026 deepfake guidelines: platform policies and detection approaches, 10,722 posts collected via systemic-risk and AI-related keywords, 500 expert-annotated posts, and controlled uploads of outputs from ten popular generative AI tools. Findings: AI labelling is now broadly established and all four platforms auto-label, with more platform-applied labels than earlier audits; but only 33% of expert-identified deepfakes in systemic-risk contexts carried a platform label while reaching a median 160,000 views; in controlled uploads carrying standard AI provenance signals, platforms labelled only 61%, and they commonly STRIP those signals after upload; rules, label designs, detection and reporting diverge substantially. Creator implications: (1) do not rely on C2PA/SynthID to trigger a label - apply the platform's own disclosure tool where required (TikT...
• articleHow does TikTok say its For You feed ranks videos, and does follower count matter?
  TikTok newsroom (2020-06-18, still served 2026-10-23): For You ranking combines user interactions (likes, shares, follows, comments, content created), video information (captions, sounds, hashtags) and device/account settings (language, country, device type; weighted lower); signals are weighted by value - finishing a longer video is a strong signal vs weak ones such as creator and viewer being in the same country; follower count and previous high-performing videos are explicitly "not direct factors", though accounts with more followers are likely to get more views; the feed intersperses diversity (generally not two videos in a row with the same sound or creator). Current FYF eligibility standards (released 2026-08-25, effective 2026-09-24) prioritize safety, may exclude content from the FYF while it stays findable via search/profile, and note low views do not necessarily mean a rule was broken; together with the Integrity rules, unoriginal/reused material is FYF-ineligible (C3-B363...
• articleWhat does HeyGen document for its HeyGen Video model and avatar engines (limits, prompting, reproducibility, consent)?
  HeyGen developer docs (captured 2026-10-23): "HeyGen Video" (heygen-video-1) is HeyGen's general-purpose video model "built on MiniMax H3 and post-trained by HeyGen" (consistent with AA listing HeyGen Video 1 at Elo 1160, $2.40/min, C3-B369-01). Modes: text-to-video, image-to-video (image is the literal first frame) and reference-to-video (reference order becomes <Picture 1>, <Picture 2>...; only the first 5 s of each reference video are read - trim to the 5 s you want). Duration 5-30 s for text/image-to-video with turbo/quality enhancement, 5-15 s for reference-to-video, ultraquality, or via MCP; resolutions 480p/768p/1080p/2k with 1080p and 2k billed at 3x the 768p rate. Prompting tips in the docs: add "no retouching, no beauty filter, no glamour lighting" to avoid retouched faces; audio is generated from the prompt, so specify room tone, effects and distance, and say "no music" to avoid an unwanted bed; set an explicit seed to make a prompt reproducible and change one clause at a...
• articleWhich AI outputs does Adobe indemnify? Firefly models vs partner models (Google, OpenAI) in Firefly Creative Production for Enterprise
  Primary help page (enterprise scope only). Partner models offered in Firefly Creative Production for Enterprise include Google Gemini 3 (Nano Banana Pro), Gemini 3.1 (Nano Banana 2), Veo, and OpenAI GPT image models incl. GPT Image 1.5 and GPT Image 2; Firefly's web docs also list video generation with Veo, Luma, Runway and Kling partner models (navigation). Indemnity: for ELIGIBLE, GENERALLY AVAILABLE Google and OpenAI media models surfaced there, Adobe indemnifies certain COPYRIGHT infringement claims under the customer's Adobe terms; this differs from Firefly-model indemnification and does NOT cover trademark, publicity or privacy claims; it can be void if the customer knew or should have known an output infringed, lacked input rights, or ignored safety features; beta/preview/early-access models are excluded and coverage "should not be assumed" for other models, providers or Adobe products. Third-party models wired in via custom nodes/actions with your own API key fall under the ...
• articleR1 export step: "An AI-generated label is added to all exported videos", with a pointer to TikTok ad policy - so Symphony output is labelled at source regardless of whether the advertiser also discloses sponsorship. R2: the help URL for generating a custom avatar now redirects (query flag...
  R1 export step: "An AI-generated label is added to all exported videos", with a pointer to TikTok ad policy - so Symphony output is labelled at source regardless of whether the advertiser also discloses sponsorship. R2: the help URL for generating a custom avatar now redirects (query flag "redirected=2") to the general avatar guide, which documents only library voiceover avatars ("Real-human or AI-generated") and product avatars. Search-located secondary sources (not re-read) describe earlier custom avatars that only the depicted person could create after identity verification, and stock avatars based on licensed paid actors; whether custom avatars still exist outside the help centre was not verified. The Creative GenAI Terms that govern output ownership were not located in full text (follow-up kept open from C3-B536-01).
• articleHow HeyGen gates real-person digital twins: consent video levels, identity matching, and the enterprise "skip consent with indemnity" option
  Closes the HeyGen consent follow-up. Every video-based "digital twin" requires proof the depicted person agreed; photo-based and prompt-generated avatars (no identifiable real person) have no consent step (consent_status null). Three access levels (developer docs): (1) webcam recording on HeyGen's hosted consent page - all customers; the API (POST /v3/avatars/{group_id}/consent) returns a link valid 24 h for the subject, who reads a statement (with a spoken code in the interactive flow); (2) uploading a pre-recorded consent video - enterprise only; (3) skipping consent entirely - enterprise only with a signed indemnity agreement. Requirements: the same person as the training footage (identity-matched), one clearly visible face, the provided statement read (validated semantically, any language), under 35 s per developer docs (help centre says under 30 s - version discrepancy), MP4/MOV/WebM, good light and audio, no recording of a screen; if creating a twin of someone else, that perso...

More