{ "checkedDate": "2026-11-03", "total": 67, "groups": { "Artists and processes": 20, "Books and institutions": 19, "Workflows and papers": 20, "Frameworks and context": 8 }, "evidence": { "opened": 66, "search-only": 1 }, "processDepth": { "detailed": 36, "partial": 28, "showcase": 3 }, "notPreviouslyLinkedInEarlierNotes": 67, "items": [ { "id": "ART01", "title": "Painting as a recursive feedback loop: Isle of Vitr∴ous", "creator": "WangShui; interview by Sarah Cascone", "url": "https://news.artnet.com/art-world/wangshui-whitney-biennial-ai-2113270", "sourceType": "firsthand interview", "year": "2022", "checkedDate": "2026-11-03", "access": "free interview text opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: oil on abraded aluminium. AI produces new images from previous paintings. WangShui sketches, collages and abrades those images into metal, adds thin oil layers, and improvises throughout; programmers collaborate on the systems.", "practicalTakeaway": "A generated image can be an intermediate drawing that an artist materially transforms.", "caveat": "The painting workflow is explicit; its exact model and training recipe are not. Process relevance does not establish aesthetic fit.", "tags": [ "painting", "oil", "aluminium", "drawing", "collage", "human finishing", "recursive workflow" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART02", "title": "How I taught an AI to think like a painter", "creator": "David Salle; with technologist Grant Davis", "url": "https://mail.davidsallestudio.net/%2725%20Financial%20Times_How%20I%20Taught%20AI_May.pdf", "sourceType": "artist process", "year": "2025", "checkedDate": "2026-11-03", "access": "free studio-hosted PDF; six pages opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: paintings over printed canvas backgrounds. Salle describes staged training-data choices and an image-variation control in Wand. He selects promising generated scenes, prints them onto canvas, and paints figurative layers over them.", "practicalTakeaway": "Separate the generated underlayer from the artist's decisions about edges, colour, composition and painted intervention.", "caveat": "His account includes other painters in early training, then his own work. It is not proof that five photographs suffice.", "tags": [ "painting", "canvas", "printed underlayer", "human finishing", "artist archive", "Wand" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART03", "title": "Art and Software Run as Parallel Tracks in the Life of Helena Sarin", "creator": "Helena Sarin; AOTM interview", "url": "https://aotm.gallery/art-and-software-run-as-parallel-tracks-in-the-life-of-helena-sarin/", "sourceType": "firsthand interview", "year": "2022", "checkedDate": "2026-11-03", "access": "free interview page opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: artist books and ceramics. Sarin trains models on her art and photography, extends pipelines through post-processing, and edits images into books. She describes potteryGAN as returning digital AI designs to physical artifacts.", "practicalTakeaway": "Treat generation, editing, sequencing and making an object as separate authored stages.", "caveat": "The interview explains the overall pipeline; it does not provide a reproducible clay construction, glaze or firing recipe.", "tags": [ "ceramics", "artist book", "GAN", "own photographs", "post-processing", "physical output" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART04", "title": "Human Allocation of Space and Figures: documented drawing-to-object processes", "creator": "Scott Eaton", "url": "https://www.nvidia.com/en-us/research/ai-art-gallery/artists/scott-eaton/", "sourceType": "artist process", "year": "2019 works; page undated", "checkedDate": "2026-11-03", "access": "free artist presentation opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: hand drawing, archival prints and bronze. Custom GANs translate Eaton's drawings into rendered bodies or geometric volumes. He authors source photography and detailed drawings; sculpture output is converted to polygons, printed, moulded and cast.", "practicalTakeaway": "A clear hand-drawn structure can remain central while a learned system supplies a different representational layer.", "caveat": "Figurative/anatomical methods do not establish abstract-painting fidelity; substantial custom datasets and fabrication are involved.", "tags": [ "drawing", "photography", "bronze", "print", "image-to-image", "human structure" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART05", "title": "Shared Visual Abstractions", "creator": "Tom White", "url": "https://arxiv.org/html/1912.04217v1", "sourceType": "artist process", "year": "2019", "checkedDate": "2026-11-03", "access": "open paper; HTML methods opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: abstract ink prints. A constrained drawing system searches stroke placement, thickness and colour using responses from trained image classifiers. White designs the drawing vocabulary and experiments; photographs of physical prints test recognition across models.", "practicalTakeaway": "Restricting marks and colours can be an artistic decision, independent of a generator's realism.", "caveat": "The paper measures classifier responses and a small human label-matching survey; neither measures beauty or usefulness to Iana.", "tags": [ "abstraction", "ink print", "constraints", "classifier feedback", "research paper" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "correction-needed", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART06", "title": "In Silico / Technical Images", "creator": "Casey Reas; Erika Weitz on Technical Images", "url": "https://reas.com/in-silico", "sourceType": "artist process", "year": "2024–2025 works", "checkedDate": "2026-11-03", "access": "free artist process page opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: wet-plate collodion photographs, aluminium prints and software. Reas curates plant scans, microscopy and landscape imagery for GAN training and selects outputs. With Weitz, generated images become collodion plates; RGB channels are separately photographed and recombined.", "practicalTakeaway": "Physical translation and channel-level recomposition can contribute as much as image synthesis.", "caveat": "Botanical imagery is contextual here, not an aesthetic recommendation. The page documents stages without a complete executable workflow.", "tags": [ "photography", "collodion", "aluminium", "physical output", "dataset curation", "GAN" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART07", "title": "Fall of the House of Usher I and II", "creator": "Anna Ridler", "url": "https://dam.org/museum/artists_ui/artists/ridler-anna/fall-house-usher/", "sourceType": "institutional project", "year": "2017", "checkedDate": "2026-11-03", "access": "free museum page; artist-authored text opened", "evidence": "opened", "processDepth": "partial", "summary": "Medium: ink drawing dataset and animation. Ridler makes more than 200 drawings after the 1929 film; interconnected GANs generate stills and feedback material for subsequent training sets. The handmade dataset is also an exhibited work.", "practicalTakeaway": "Preparatory drawings and dataset construction can remain visible parts of the finished project.", "caveat": "This is intentionally horror/uncanny work, included for process rather than its aesthetic; implementation details are limited.", "tags": [ "drawing", "ink", "animation", "handmade dataset", "archive", "horror aesthetic" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART08", "title": "My Artificial Muse", "creator": "Albert Barqué-Duran, Mario Klingemann and Marc Marzenit", "url": "https://albert-data.com/pages/my-artificial-muse", "sourceType": "artist process", "year": "2017 documented Sónar+D performance; current project-page body says 2016", "checkedDate": "2026-11-03", "access": "free artist project page opened", "evidence": "opened", "processDepth": "partial", "summary": "Medium: live oil painting, projected neural generation and sound. A neural network produces a classical-style image; Barqué-Duran interprets it in paint. Embodied sensors connect his movement with a generative soundscape.", "practicalTakeaway": "Painting can be a selective human interpretation of an AI proposal, rather than a literal transfer.", "caveat": "The current project page inconsistently says 2016 and 2017; a collaborator account and the artist exhibition list document a 2017 performance. The inception/premiere conflict remains unresolved. Model settings and a painting recipe are absent.", "tags": [ "oil painting", "performance", "human interpretation", "neural generation", "sound" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "correction-needed", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART09", "title": "Reflection: cameras and physical feedback in robotic painting", "creator": "Pindar Van Arman; artist-hosted essay by centoshi", "url": "https://www.vanarman.com/reflection", "sourceType": "artist process", "year": null, "checkedDate": "2026-11-03", "access": "free artist-hosted process essay opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: paintings on stretched canvas. Cameras observe marks and multiple algorithms evaluate the changing image before the robot makes further marks. Physical paint variation becomes input; Van Arman authors and revises the robotic system.", "practicalTakeaway": "The material surface can feed back into computational decisions instead of merely receiving a finished digital image.", "caveat": "Claims about machine creativity are the artists' interpretation. The page does not supply a reproducible control implementation.", "tags": [ "painting", "robotics", "camera feedback", "physical material", "canvas" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART10", "title": "Tabula Rasa: an artist's account of training on solid colours", "creator": "David Young", "url": "https://writings.davidyoung.art/tabula-rasa/", "sourceType": "artist process", "year": "2019 original essay", "checkedDate": "2026-11-03", "access": "free artist essay opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: abstract generated images. Young begins GAN training with one black image, then adds further solid colours and observes resulting textures, grids and shapes. He authors the restricted material and compares stages of the system's development.", "practicalTakeaway": "An AI investigation can begin with colour and compositional constraints, without imitating a painter's complete style.", "caveat": "Machine emotion is an acknowledged metaphor, not a demonstrated mental state; the essay is not a current software tutorial.", "tags": [ "abstraction", "colour", "minimal dataset", "GAN", "artist essay" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART11", "title": "Hallucinations / Adversarially Evolved Hallucinations", "creator": "Trevor Paglen", "url": "https://paglen.studio/2020/04/09/hallucinations/", "sourceType": "artist process", "year": "2017 works; 2020 page", "checkedDate": "2026-11-03", "access": "free artist page opened", "evidence": "opened", "processDepth": "partial", "summary": "Medium: synthetic images and dye-sublimation prints. Paglen constructs training categories from literature, history and other conceptual corpora, trains recognition systems, then uses adversarial generation to produce images satisfying those systems.", "practicalTakeaway": "Choosing what categories a system can recognise can be a substantive part of the artwork's argument.", "caveat": "The artist explains the conceptual pipeline; architecture and training details are absent. Some imagery is disturbing.", "tags": [ "print", "dataset authorship", "classification", "GAN", "critical practice" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART12", "title": "Zizi — Queering the Dataset", "creator": "Jake Elwes", "url": "https://www.jakeelwes.com/project-zizi-2019.html", "sourceType": "artist process", "year": "2019", "checkedDate": "2026-11-03", "access": "free artist project page opened", "evidence": "opened", "processDepth": "partial", "summary": "Medium: multichannel video. Elwes retrains a StyleGAN model originally trained on FFHQ with 1,000 additional images of drag and gender-fluid faces. Dataset intervention changes the model's visual vocabulary; Elwes authors framing and installation.", "practicalTakeaway": "Dataset additions can deliberately challenge what a pretrained model treats as normal.", "caveat": "Historical online-image collection is described, not offered as a permissions precedent. No exact retraining recipe is provided.", "tags": [ "video", "portrait", "dataset intervention", "drag", "StyleGAN", "critical practice" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART13", "title": "Wearing, Gillian: museum production account", "creator": "Gillian Wearing with Wieden + Kennedy", "url": "https://www.guggenheim.org/wp-content/uploads/2021/11/guggenheim-gillian-wearing-wearing-masks-digital-wall-text.pdf", "sourceType": "institutional project", "year": "2018 work; 2021 wall text", "checkedDate": "2026-11-03", "access": "free museum PDF; relevant work entry examined", "evidence": "opened", "processDepth": "partial", "summary": "Medium: five-minute colour film. Wearing casts more than fifteen performers to portray her; their faces, bodies and voices are digitally combined with hers into a deepfake persona. Casting, scripting and performance remain human-authored.", "practicalTakeaway": "AI-mediated identity can be built around authored performances and a script, rather than anonymous generated footage.", "caveat": "The relevant wall-text entry was read, not the entire 82-page PDF. The neural model and compositing pipeline are unspecified.", "tags": [ "film", "performance", "deepfake", "identity", "museum documentation" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART14", "title": "Dio: Media and Materiality", "creator": "Ben Snell; Phillips interview/account", "url": "https://www.phillips.com/article/42361496/media-and-materiality-in-conversation-with-ben-snell", "sourceType": "firsthand interview", "year": "2018 work; 2019 interview", "checkedDate": "2026-11-03", "access": "free interview/account opened", "evidence": "opened", "processDepth": "partial", "summary": "Medium: physical sculpture. Snell trains a system with 3D models of classical sculpture, then makes its generated form from the powdered components of the computer itself. He authors training selection, fabrication and the material narrative.", "practicalTakeaway": "The output material can express the concept behind an AI process rather than simply illustrate its result.", "caveat": "The source describes classical 3D training models and casting computer powder mixed with clear resin; architecture and a complete fabrication specification are absent. Its autonomy language is promotional.", "tags": [ "sculpture", "3D dataset", "material concept", "physical output" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "correction-needed", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART15", "title": "Cloud of Petals: artist conversation on collection, film and VR", "creator": "Sarah Meyohas; interview by Maisie Skidmore", "url": "https://www.anothermag.com/art-photography/10266/the-artist-using-an-algorithm-to-generate-rose-petals", "sourceType": "firsthand interview", "year": "2017", "checkedDate": "2026-11-03", "access": "free artist conversation opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: photography, 16mm film, a pressed-petal archive and VR. Workers photograph 100,000 petals and select favourites; Meyohas films their labour and works with ML specialists on generated petals. Human selection persists in the physical archive.", "practicalTakeaway": "Source collection, labour and subjective selection can become visible elements of the artwork.", "caveat": "This does not demonstrate botanical imagery suits Iana. The source documents stages but omits training parameters.", "tags": [ "photography", "archive", "film", "VR", "data collection", "human selection" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART16", "title": "Not the Only One (N'TOO)", "creator": "Stephanie Dinkins", "url": "https://www.stephaniedinkins.com/ntoo.html", "sourceType": "artist process", "year": "2018 work; 2021 model update described", "checkedDate": "2026-11-03", "access": "free artist project and technical notes opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: voice-interactive sculpture/archive. Oral histories from three generations of Dinkins's family and culturally attuned material inform a conversational AI. The artist records, selects and aligns material, designs the entity, and iterates its model and sculptural embodiment.", "practicalTakeaway": "An authored archive may include voices and histories, with usefulness judged against the represented people's needs.", "caveat": "Dinkins describes imperfect responses and model changes. This is an archival/social practice, not evidence for painting-style transfer.", "tags": [ "oral history", "archive", "sculpture", "NLP", "community", "small data" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART17", "title": "The Call", "creator": "Holly Herndon and Mat Dryhurst; Serpentine Arts Technologies and participating choirs", "url": "https://www.serpentinegalleries.org/whats-on/holly-herndon-mat-dryhurst-the-call/", "sourceType": "institutional project", "year": "2024–2025", "checkedDate": "2026-11-03", "access": "free institutional project page and credits opened", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: choral sound installation. A composed songbook and recording protocol guide sessions with fifteen community choirs; recordings train choral AI models. Artists, singers, researchers and designers author different stages, with contributor governance explored through a Data Trust.", "practicalTakeaway": "Design source-making and contributors' roles before treating a model as the artwork's sole author.", "caveat": "Sound and collective governance are the transferable ideas; this is not a visual painting workflow or a checked public model service.", "tags": [ "sound", "participation", "authored dataset", "consent", "choral AI", "installation" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART18", "title": "Artificial Life: a process interview", "creator": "Sofia Crespo; interview by Andrew Dubber, MTF Labs", "url": "https://shows.acast.com/mtflabs/episodes/67ceea6dd64d9d8e86dc852e", "sourceType": "firsthand interview", "year": "2021", "checkedDate": "2026-11-03", "access": "free podcast transcript opened; audio not auditioned", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: synthetic-organism imagery and video. Crespo explains collecting subject-specific datasets, training separate caterpillar and butterfly models, then connecting their nearest visual states. She authors datasets, transitions and selection among many generated alternatives.", "practicalTakeaway": "Separate models or collections can provide different visual vocabularies whose relationship the artist composes.", "caveat": "Organic/uncanny forms are contextual, not recommended aesthetics. The transcript was examined; no model or audio was run.", "tags": [ "video", "dataset curation", "synthetic biology", "GAN", "organic aesthetic" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART19", "title": "The Substitute", "creator": "Alexandra Daisy Ginsberg; animation by The Mill", "url": "https://www.daisyginsberg.com/work/the-substitute", "sourceType": "artist process", "year": "2019", "checkedDate": "2026-11-03", "access": "free artist project page opened", "evidence": "opened", "processDepth": "partial", "summary": "Medium: paired video installation. A rendered rhino's behaviour is based on DeepMind agent research; animal behaviours and sounds are adapted from research footage. Ginsberg and collaborators author the ecological premise, animation and dual-screen presentation.", "practicalTakeaway": "AI-derived behaviour can serve a specific conceptual question rather than operate as decorative movement.", "caveat": "The artist credits animation based on research; this page does not establish a live-learning system in the gallery.", "tags": [ "video", "animation", "agent research", "ecology", "contextual reference" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "ART20", "title": "Feminist Data Set: toolkit and process", "creator": "Caroline Sinders", "url": "https://carolinesinders.com/wp-content/uploads/2020/05/Feminist-Data-Set-Final-Draft-2020-0526.pdf", "sourceType": "artist process", "year": "2020 reader; project begun 2017", "checkedDate": "2026-11-03", "access": "free artist toolkit PDF; process and workshop sections examined", "evidence": "opened", "processDepth": "detailed", "summary": "Medium: participatory workshops, archive and toolkit. People define categories and submit material; Sinders reviews submissions and adjusts subsequent collection to address exclusions. The artwork examines human decisions throughout a future machine-learning pipeline.", "practicalTakeaway": "Collecting, naming, rejecting and documenting source material can be artistic work in its own right.", "caveat": "The reader explicitly presents a complete feminist AI as prospective. This is upstream AI-art practice, not a finished generative-image system.", "tags": [ "archive", "workshop", "data curation", "participation", "upstream practice", "critical practice" ], "group": "Artists and processes", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT01", "title": "Digital Art, fourth edition", "creator": "Christiane Paul", "url": "https://thamesandhudsonusa.com/books/digital-art-softcover-fourth", "sourceType": "book", "year": "2023", "checkedDate": "2026-11-03", "access": "Publisher metadata and description opened; sample-spread links present but not inspected; full book not retrieved.", "evidence": "opened", "processDepth": "partial", "summary": "A historical and critical survey covering digital media's relationship to painting, print, photography and sculpture, alongside AI, installation and collecting.", "practicalTakeaway": "Use it to choose an artistic lineage and presentation medium before choosing software.", "caveat": "Broad digital-art history, with AI as one topic; not a contemporary image-generator or painting manual. Assessment is based on the publisher description.", "tags": [ "AI and adjacent digital art", "history", "theory", "painting", "physical output" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT02", "title": "Artificial Aesthetics: Generative AI, Art and Visual Media", "creator": "Lev Manovich and Emanuele Arielli", "url": "https://manovich.net/index.php/projects/artificial-aesthetics", "sourceType": "book", "year": "2024; collected PDF posted 2025", "checkedDate": "2026-11-03", "access": "Free author-hosted 194-page complete PDF retrieved; front matter, contents and selected passages inspected; not read cover-to-cover.", "evidence": "opened", "processDepth": "partial", "summary": "Essays examine creative agency, aesthetic judgment, perception, media history and the status of AI images.", "practicalTakeaway": "Create a studio rubric separating visual appeal, personal intention, authorship and useful surprise.", "caveat": "Critical theory rather than a software manual. The author requests a 2024 citation while dating the collected PDF January 15, 2025. Not read cover-to-cover.", "tags": [ "AI art", "open access", "theory", "aesthetics", "evaluation" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT03", "title": "The Perception Machine: Our Photographic Future between the Eye and AI", "creator": "Joanna Zylinska", "url": "https://mitpress.mit.edu/9780262546836/the-perception-machine/", "sourceType": "book", "year": "2023", "checkedDate": "2026-11-03", "access": "Publisher metadata and OA notice opened; full-text endpoint returned 403 on 3 November 2026; no full book retrieved.", "evidence": "opened", "processDepth": "partial", "summary": "Connects computational photography and machine vision with perception and the author's photographic, collage, film and installation projects.", "practicalTakeaway": "Examine how photographic references and machine interpretation change a painting's point of view.", "caveat": "Theory and artistic inquiry, not a painting workflow. Open-access status is confirmed by MIT Press; the full book was not retrieved or read.", "tags": [ "AI art", "machine vision", "critical theory", "photography", "collage" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "partly-supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT04", "title": "Computational Formalism: Art History and Machine Learning", "creator": "Amanda Wasielewski", "url": "https://mitpress.mit.edu/9780262545648/computational-formalism/", "sourceType": "book", "year": "2023", "checkedDate": "2026-11-03", "access": "Publisher metadata and OA notice opened; DiVA PDF routes timed out and institutional record denied access on 3 November 2026; no book full text retrieved.", "evidence": "opened", "processDepth": "partial", "summary": "Studies how artwork datasets, style categories and machine vision shape computational art-historical analysis.", "practicalTakeaway": "Question whether a model's apparent stylistic match captures the artist's decisions or merely recurring visual features.", "caveat": "AI analysis of art is the central subject, rather than making paintings. Publisher description checked; full book not read.", "tags": [ "AI and art analysis", "datasets", "style", "critical theory", "evaluation" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "partly-supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT05", "title": "Artificial Intelligence and the Arts: Computational Creativity, Artistic Behavior, and Tools for Creatives", "creator": "Penousal Machado, Juan Romero and Gary Greenfield, editors", "url": "https://link.springer.com/book/10.1007/978-3-030-59475-6", "sourceType": "book", "year": "2021", "checkedDate": "2026-11-03", "access": "Publisher overview and table of contents opened; full chapters/book not retrieved.", "evidence": "opened", "processDepth": "partial", "summary": "Technical collection spanning visual art, music, design and games; visual-art chapters include artificial life, search-based art and neural style transfer.", "practicalTakeaway": "Ask a technical collaborator which model family fits a specific studio task instead of treating all generative systems alike.", "caveat": "Research-oriented and partly mathematical; contents were checked, not complete chapters. Predates today's image-generator interfaces.", "tags": [ "AI art", "technical reference", "style transfer", "evolutionary art", "research" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT06", "title": "Computers and Creativity", "creator": "Jon McCormack and Mark d'Inverno, editors", "url": "https://link.springer.com/book/10.1007/978-3-642-31727-9", "sourceType": "book", "year": "2012", "checkedDate": "2026-11-03", "access": "Publisher overview and table of contents opened; full chapters/book not retrieved.", "evidence": "opened", "processDepth": "partial", "summary": "Interdisciplinary collection joins computational creativity, aesthetic evaluation and artists' approaches across visual, musical and interactive work.", "practicalTakeaway": "Compare designing a system, selecting its outputs and making the final material work as different creative decisions.", "caveat": "Foundational computational-art and creativity research, including AI and evolutionary systems; not a diffusion-model guide. No full-book reading.", "tags": [ "AI and adjacent computational art", "creativity", "evaluation", "history", "research" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT07", "title": "The Practice of Art and AI: European ARTificial Intelligence Lab", "creator": "Andreas J. Hirsch, Markus Jandl and Gerfried Stocker, editors", "url": "https://hatjecantz.de/en/collections/best-selling-collection/products/59005-the-practice-of-art-and-ai", "sourceType": "book", "year": "2021", "checkedDate": "2026-11-03", "access": "Publisher record opened; print marked permanently out of stock. Ars Electronica advertises a free 6 MB PDF in search extraction, but the download page and PDF returned 403 on 3 November 2026; full book not retrieved.", "evidence": "opened", "processDepth": "partial", "summary": "Documents art-and-AI projects through the European ARTificial Intelligence Lab and Ars Electronica's art/science context.", "practicalTakeaway": "Find comparable projects and collaborators, then trace an individual project's process rather than copying its appearance.", "caveat": "Publisher record verified; catalogue contents and full book were not inspected. Do not equate an advertised archive download with successful full-text retrieval.", "tags": [ "AI art", "artist projects", "institutional practice", "art and science", "catalogue context" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "partly-supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT08", "title": "Digital Art: 1960s to Now", "creator": "Pita Arreola, Corinna Gardner and Melanie Lenz", "url": "https://www.vam.ac.uk/shop/books/design-books/digital-art-1960s-to-now-169111.html", "sourceType": "book", "year": "2024", "checkedDate": "2026-11-03", "access": "Museum shop metadata and description plus V&A research page opened; sample-spread links present but not inspected; full book not retrieved.", "evidence": "opened", "processDepth": "partial", "summary": "Decade-based history combines essays with interviews involving artists, curators, gallerists and collectors, from computer works on paper to contemporary digital practice.", "practicalTakeaway": "Study how artists move between drawings, systems, installations and institutions while retaining a coherent practice.", "caveat": "AI is part of a broader history. The V&A research-project page confirms the 2024 publication; the book was not read in full.", "tags": [ "AI and adjacent digital art", "history", "artist interviews", "works on paper", "presentation" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT09", "title": "Artistes & robots", "creator": "Laurence Bertrand Dorléac and Jérôme Neutres, editors; Grand Palais Rmn", "url": "https://editions.grandpalaisrmn.fr/fr/editions/EC107109?guid=6ab4fd0807724", "sourceType": "catalogue", "year": "2018", "checkedDate": "2026-11-03", "access": "Publisher catalogue record opened; associated 31-page teacher dossier and 8-page English visitor guide retrieved and sampled; catalogue itself not retrieved.", "evidence": "opened", "processDepth": "showcase", "summary": "Exhibition catalogue provides a route into robot-assisted and autonomous art, complemented by the institution's educational materials.", "practicalTakeaway": "Compare the role of physical gestures, autonomy and audience experience before considering robotic output.", "caveat": "French-language catalogue; book record rather than full text inspected. The exhibition includes rule-based and robotic work beyond machine learning.", "tags": [ "AI and adjacent robotic art", "catalogue", "physical output", "history", "French" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT10", "title": "Generative Art: A practical guide using Processing", "creator": "Matt Pearson", "url": "https://www.manning.com/books/generative-art", "sourceType": "book", "year": "2011", "checkedDate": "2026-11-03", "access": "Publisher metadata and 14-page sample/contents opened; full book not retrieved; code not run.", "evidence": "opened", "processDepth": "detailed", "summary": "Instructional introduction to algorithmic image making with Processing, including randomness, noise, emergence, autonomy and fractals.", "practicalTakeaway": "Build a small rule-driven study of line, spacing or rhythm as a comparison with an AI-assisted study.", "caveat": "Adjacent generative coding, not machine learning. Detailed steps are described by the publisher and contents; old code was not run or validated.", "tags": [ "adjacent computational art", "practical manual", "creative coding", "composition", "Processing" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT11", "title": "Creative AI Lab: tools, resources and R&D Labyrinths", "creator": "Serpentine Galleries and King's College London; R&D Labyrinths with Trust", "url": "https://www.serpentinegalleries.org/whats-on/creative-ai-lab/", "sourceType": "institutional archive", "year": "2020–ongoing; walkthrough series launched 2021", "checkedDate": "2026-11-03", "access": "Free Serpentine Lab and R&D Labyrinths descriptions and KCL project page opened; videos, database entries and tools not tested. Programme page remains labelled ongoing.", "evidence": "opened", "processDepth": "partial", "summary": "Research programme links tool resources, discussions and artist-led software walkthroughs. R&D Labyrinths describes step-by-step poetry, composition and governance examples.", "practicalTakeaway": "Use its walkthrough format to document source material, interface choices and artistic decisions in a painting experiment.", "caveat": "The three observed walkthrough descriptions concern poetry, music and collective governance, not painting recipes. Historical tool links may need fresh compatibility checks.", "tags": [ "AI art", "process documentation", "tools", "artist walkthroughs", "cross-media" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT12", "title": "Future Art Ecosystems 4: Art x Public AI", "creator": "Serpentine Arts Technologies, drawing on Creative AI Lab research", "url": "https://www.serpentinegalleries.org/whats-on/future-art-ecosystems-4-art-x-public-ai/", "sourceType": "institutional archive", "year": "2024", "checkedDate": "2026-11-03", "access": "Volume-specific Serpentine launch page and series overview retrieved; launch dated 19 March 2024. Full briefing reader could not be retrieved on 3 November 2026; briefing not read.", "evidence": "opened", "processDepth": "partial", "summary": "Institutional briefing examines the AI stack and cultural organisations' ability to shape AI infrastructure.", "practicalTakeaway": "Before commissioning a studio system, identify who controls data, model access, compute and continuing support.", "caveat": "Infrastructure and cultural policy, not visual technique. Programme and launch date checked; full report was not retrieved or read. This is the 2024 FAE4 volume, not the latest series volume; the series page now also lists FAE5.", "tags": [ "AI art", "infrastructure", "institutional practice", "data", "strategy" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "partly-supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT13", "title": "European ARTificial Intelligence Lab archive", "creator": "Ars Electronica and European cultural/scientific partners", "url": "https://archive.aec.at/ailab/", "sourceType": "institutional archive", "year": "2018–2021", "checkedDate": "2026-11-03", "access": "Free archive introduction opened; dynamic results remained Loading data in text extraction; no individual residency record or current application offer verified.", "evidence": "opened", "processDepth": "partial", "summary": "Historical programme archive indexes residencies, activities, partners and juries around artistic engagement with AI.", "practicalTakeaway": "Follow a residency from artistic question to scientific partnership and exhibition, looking for viable collaboration models.", "caveat": "Completed programme, not a current residency offer. The landing page does not establish process detail for every indexed project or reusable code.", "tags": [ "AI art", "residencies", "archive", "art and science", "collaboration" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT14", "title": "Renaissance 3.0: A Base Camp for New Alliances of Art and Science in the 21st Century", "creator": "ZKM | Center for Art and Media Karlsruhe; curators Peter Weibel and Anett Holzheid", "url": "https://zkm.de/en/exhibition/2023/03/renaissance-30", "sourceType": "institutional archive", "year": "2023–2024", "checkedDate": "2026-11-03", "access": "Free historical exhibition page, work catalogue index and the native picture object description opened; videos/talks not played; no current workshop availability established.", "evidence": "opened", "processDepth": "partial", "summary": "Exhibition archive follows artistic laboratories and shared art/science tools, with individual works and linked interviews.", "practicalTakeaway": "Consider how a technical experiment becomes a material artwork with a subject, duration and installation context.", "caveat": "Broad art/science and computational practice, not exclusively AI. Historical workshops listed on the page are past events; no current attendance is implied.", "tags": [ "adjacent computational art", "art and science", "archive", "materiality", "interviews" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT15", "title": "AI: More than Human", "creator": "Barbican; curators Suzanne Livingston and Maholo Uchida", "url": "https://www.barbican.org.uk/hire/exhibition-touring-barbican-immersive/ai-more-than-human", "sourceType": "institutional archive", "year": "2019 original exhibition; touring resource", "checkedDate": "2026-11-03", "access": "Free touring overview and original 2019 event archive opened; interview/essay links observed but media not played. Hire availability from mid-April 2027 is institutional touring information.", "evidence": "opened", "processDepth": "showcase", "summary": "Exhibition places artistic commissions alongside scientific AI research and questions about human-machine relationships.", "practicalTakeaway": "Use artist interviews to compare the intended experience of an artwork with the technical system producing it.", "caveat": "A survey rather than a production manual. The original 2019 exhibition is past; the current touring-hire page is not a current public exhibition listing.", "tags": [ "AI art", "exhibition", "artist interviews", "critical context", "audience experience" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT16", "title": "Chance and Control: Art in the Age of Computers", "creator": "Victoria and Albert Museum", "url": "https://www.vam.ac.uk/exhibitions/chance-and-control-art-in-the-age-of-computers", "sourceType": "institutional archive", "year": "2018", "checkedDate": "2026-11-03", "access": "Free past-display overview and artwork highlights opened; 2-page conference programme retrieved (26 October 2018); no procedural manual or current enrollment.", "evidence": "opened", "processDepth": "showcase", "summary": "Displays computer-generated prints, drawings and paintings by artists including Vera Molnár, Frieder Nake, Manfred Mohr and Roman Verostko.", "practicalTakeaway": "Compare controlled variation in line and composition with a hand-painted series, using actual works on paper as references.", "caveat": "Predominantly adjacent algorithmic art, not evidence about modern learned image models. Past display and conference; no procedural reproduction instructions.", "tags": [ "adjacent computational art", "history", "works on paper", "composition", "archive" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT17", "title": "A Shift in Artistic Practices through Artificial Intelligence", "creator": "Kıvanç Tatar, Petter Ericson, Kelsey Cotton, Paola Torres Núñez del Prado, Roser Batlle-Roca, Beatriz Cabrero-Daniel, Sara Ljungblad, Georgios Diapoulis and Jabbar Hussain", "url": "https://aicomparts.com/projects/2024-leonardo/", "sourceType": "journal", "year": "2024; preprint first posted 2023", "checkedDate": "2026-11-03", "access": "Author page and arXiv metadata opened; free 13-page author-deposited manuscript PDF retrieved and sampled. Former five-page UPF published-PDF endpoint returned 502 on 3 November 2026; publisher DOI returned 403.", "evidence": "opened", "processDepth": "partial", "summary": "Leonardo article surveys how accessible AI systems challenge artistic roles, conventions and practices across media.", "practicalTakeaway": "Name which studio roles a system changes: proposing, selecting, composing, producing or performing.", "caveat": "Short field overview, not a controlled study demonstrating improved paintings or a complete production recipe. Published article and preprint dates differ.", "tags": [ "AI art", "journal", "artistic practice", "cross-media", "open access" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "partly-supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT18", "title": "Creative Applications of Deep Learning with TensorFlow", "creator": "Parag Mital; Kadenze", "url": "https://www.kadenze.com/courses/creative-applications-of-deep-learning-with-tensorflow/info", "sourceType": "course", "year": "2016", "checkedDate": "2026-11-03", "access": "Historical Kadenze syllabus and Enrollment Closed label verified only through search extraction; direct page fetch timed out on 3 November 2026. Author-owned archived CADL README and notebook index opened; video access/enrollment and code compatibility untested.", "evidence": "search-only", "processDepth": "partial", "summary": "Syllabus describes dataset preparation, network building, generative models and creative applications using an early TensorFlow stack.", "practicalTakeaway": "Use its dataset-to-model-to-experiment structure when discussing a learning plan with a technical collaborator.", "caveat": "Historical technical course, not a verified current class. Canonical page lists TensorFlow 0.11.0; the separate -i offering lists 0.9.0. Dataset, network, DeepDream/style-transfer and generative-model lessons are historical instruction, not physical painting technique.", "tags": [ "AI art", "archived course", "technical education", "datasets", "historical software" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "unverifiable-current-access", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LIT19", "title": "CODE 2024: Deep Nudes and Digital Oblivion", "creator": "IMPAKT Centre for Media Culture and collaborating artists/partner organisations", "url": "https://impakt.nl/events/2024/exhibition/code-2024/", "sourceType": "institutional archive", "year": "2024", "checkedDate": "2026-11-03", "access": "Free exhibition archive and project list opened; individual project workflows not retrieved; physical exhibition and artist talks took place in 2024.", "evidence": "opened", "processDepth": "partial", "summary": "Documents a collaborative art programme addressing AI images, digital identity, opaque models and control over personal data.", "practicalTakeaway": "Choose a concrete artistic question about representation or agency before building an AI intervention.", "caveat": "Critical media-art projects rather than painter-facing technique. A six-month co-creation process is documented, but the overview does not provide complete technical workflows.", "tags": [ "AI art", "critical practice", "digital identity", "collaboration", "archive" ], "group": "Books and institutions", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB01", "title": "InvokeAI: Crafting images with the Canvas", "creator": "InvokeAI contributors", "url": "https://v7.invoke.ai/users-guide/canvas/introduction/", "sourceType": "official workflow", "year": null, "checkedDate": "2026-11-03", "access": "free documentation; application/model setup not tested", "evidence": "opened", "processDepth": "detailed", "summary": "A raster painting, mask and regional guidance become candidate edits, staged for acceptance into layers.", "practicalTakeaway": "The artist draws masks, adjusts denoising and accepts or discards results. An abstract painter could isolate one unresolved passage.", "caveat": "Versioned v7 documentation; controls depend on model support. Documented masking does not establish fidelity to an individual practice.", "tags": [ "artist-directed-editing", "own-reference-style", "hands-on", "layers", "inpainting" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB02", "title": "ComfyUI inpainting and outpainting examples", "creator": "ComfyUI project", "url": "https://comfyanonymous.github.io/ComfyUI_examples/inpaint/", "sourceType": "official workflow", "year": null, "checkedDate": "2026-11-03", "access": "free examples with embedded workflows; checkpoints not downloaded", "evidence": "opened", "processDepth": "detailed", "summary": "An image and alpha mask feed an editable node workflow; padding extends its bounds for outpainting.", "practicalTakeaway": "The artist chooses the editable region and inspects workflow parameters. Useful for making variations around a retained painted fragment.", "caveat": "These examples name older v2/AnythingV3 checkpoints. Loading workflow metadata is documented; compatibility with a fresh installation was not tested.", "tags": [ "artist-directed-editing", "hands-on", "inpainting", "outpainting", "embedded-workflow" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB03", "title": "Photoshop: Use reference images for consistent results", "creator": "Adobe", "url": "https://helpx.adobe.com/photoshop/desktop/create-open-import-images/create-images/use-reference-images-for-consistent-results.html", "sourceType": "official workflow", "year": "2026", "checkedDate": "2026-11-03", "access": "free instructions; Photoshop and generation access separate", "evidence": "opened", "processDepth": "detailed", "summary": "A selection plus uploaded reference guides Generative Fill; the guide distinguishes whole-image/object references and placing/swapping content.", "practicalTakeaway": "The artist supplies both region and example. Try one approved motif as reference, then compare candidates against a manually composed study.", "caveat": "Commercial application and model-specific options; this manual demonstrates controls, not exact copying, style fidelity or a verified free generation entitlement.", "tags": [ "artist-directed-editing", "own-reference-style", "hands-on", "reference-image", "commercial-tool" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB04", "title": "Draw Things Basic UI guide", "creator": "Draw Things community documentation contributors", "url": "https://github.com/drawthingsai/community-docs/blob/main/Documentation.docc/1.UI.md", "sourceType": "creator-hosted community guide", "year": null, "checkedDate": "2026-11-03", "access": "free community guide hosted by tool creator", "evidence": "opened", "processDepth": "detailed", "summary": "The guide covers canvas drawing, imported images, inpainting, seeds, project history and configuration templates.", "practicalTakeaway": "The artist retains drawing, erasing, strength and seed choices. It offers a route from a rough colour sketch to saved alternatives.", "caveat": "Community-authored, with an explicitly old UI section. Treat historical resolutions and button locations as version-specific; application and models were not tested.", "tags": [ "artist-directed-editing", "hands-on", "sketch-to-image", "local-workflow", "community-authored" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB05", "title": "Diffusers: Image-to-image", "creator": "Hugging Face Diffusers maintainers", "url": "https://huggingface.co/docs/diffusers/using-diffusers/img2img", "sourceType": "official workflow", "year": null, "checkedDate": "2026-11-03", "access": "free documentation with executable code examples; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "A starting image and prompt produce a transformed image; examples vary strength, guidance and model family.", "practicalTakeaway": "The artist chooses the initial block-in and change amount. A small strength sweep could reveal when useful variation becomes unwanted rewriting.", "caveat": "Python/model setup is required. Examples use specific diffusion architectures; a strength value is not a portable percentage of artistic fidelity.", "tags": [ "artist-directed-editing", "hands-on", "image-to-image", "parameter-study" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB06", "title": "SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations", "creator": "Chenlin Meng and colleagues", "url": "https://chenlin9.github.io/SDEdit/", "sourceType": "paper/project", "year": "2021; ICLR 2022", "checkedDate": "2026-11-03", "access": "open paper, project and original code; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "Coloured strokes or a rough composite are noised and denoised into image variants using a pretrained diffusion prior.", "practicalTakeaway": "The artist supplies the arrangement and edits; its noise-versus-retention tradeoff explains why a block-in can guide without precisely constraining output.", "caveat": "Original checkpoints target faces, bedrooms and churches. Realism-oriented results do not establish suitability for preserving abstract marks.", "tags": [ "artist-directed-editing", "sketch-to-image", "foundational", "image-to-image" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB07", "title": "IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models", "creator": "Hu Ye and colleagues; Tencent AI Lab", "url": "https://github.com/tencent-ailab/IP-Adapter", "sourceType": "paper/project", "year": "2023", "checkedDate": "2026-11-03", "access": "open paper and official code/notebooks; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "A reference image conditions generation alongside text, without training a new adapter for each supplied image.", "practicalTakeaway": "The artist chooses references and image influence. Compare reference-guided motif or palette studies before committing to training on an archive.", "caveat": "Adapters must match their base architecture. Original defaults center-crop references, potentially losing peripheral marks; similarity is not an authorship/style guarantee.", "tags": [ "own-reference-style", "artist-directed-editing", "reference-image", "adapter" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB08", "title": "DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation", "creator": "Nataniel Ruiz and colleagues; Google Research", "url": "https://dreambooth.github.io/", "sourceType": "paper/project", "year": "2022; CVPR 2023", "checkedDate": "2026-11-03", "access": "open original paper/project; separate Diffusers training implementation opened", "evidence": "opened", "processDepth": "detailed", "summary": "A selected subject-image set fine-tunes a model, associating an identifier with that subject for new renditions.", "practicalTakeaway": "The artist authors the training set and judges retained identity. Useful background for recurring personal motifs, rather than automatic style certification.", "caveat": "Original work used Imagen; linked Diffusers training is a separate implementation. Few-image subject experiments do not establish a universal painting-dataset minimum.", "tags": [ "own-reference-style", "personalization", "training", "foundational" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB09", "title": "Training Generative Adversarial Networks with Limited Data / StyleGAN2-ADA", "creator": "Tero Karras and colleagues; NVIDIA", "url": "https://github.com/NVlabs/stylegan2-ada-pytorch", "sourceType": "paper/project", "year": "2020; PyTorch implementation 2021", "checkedDate": "2026-11-03", "access": "open paper and official training code; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "A curated dataset trains or fine-tunes a GAN; adaptive augmentation addresses discriminator overfitting under limited data.", "practicalTakeaway": "The artist controls archive selection and sample curation. Useful for understanding dataset-shaped visual worlds and interpolation, beyond text prompting.", "caveat": "Historical CUDA/PyTorch stack. Limited-data experiments are not evidence that five artwork photographs reliably capture an artist’s practice.", "tags": [ "own-reference-style", "training", "gan", "dataset-authorship" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB10", "title": "InstructPix2Pix: Learning to Follow Image Editing Instructions", "creator": "Tim Brooks, Aleksander Holynski and Alexei A. Efros", "url": "https://www.instruct-pix2pix.timothybrooks.com/", "sourceType": "paper/project", "year": "2022; CVPR 2023", "checkedDate": "2026-11-03", "access": "open paper, project and official code; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "An existing image plus an editing instruction produces an edited image without per-image fine-tuning or inversion.", "practicalTakeaway": "The artist specifies a change and rejects collateral changes. Compare a single palette/material instruction with a manually painted counterpart.", "caveat": "The project shows excessive edits and failures to isolate objects or reorganize scenes. Its 2023 model is a historical baseline.", "tags": [ "artist-directed-editing", "instruction-editing", "foundational" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB11", "title": "DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing", "creator": "Yujun Shi and colleagues", "url": "https://yujun-shi.github.io/projects/dragdiffusion.html", "sourceType": "paper/project", "year": "2023; CVPR 2024", "checkedDate": "2026-11-03", "access": "open paper, project and official UI code; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "An image, editable mask and handle/target points produce a spatially deformed image through latent optimization.", "practicalTakeaway": "The artist chooses where a form moves. Potentially useful for studying spacing or silhouette shifts without describing them in prose.", "caveat": "Original real-image workflow first trains an image-specific LoRA; documented setup targets NVIDIA/Linux and an older Diffusers version.", "tags": [ "artist-directed-editing", "hands-on-research", "point-editing", "composition" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB12", "title": "Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation", "creator": "Narek Tumanyan, Michal Geyer, Shai Bagon and Tali Dekel", "url": "https://pnp-diffusion.github.io/", "sourceType": "paper/project", "year": "2022; CVPR 2023", "checkedDate": "2026-11-03", "access": "open paper, project and official code; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "A source image and target prompt yield a translated image, with source features injected to retain semantic layout.", "practicalTakeaway": "The artist supplies composition and chooses structural influence. Compare surface or colour alternatives while checking that key relationships survive.", "caveat": "Original code targets Stable Diffusion v1.4. Layout preservation can leak source appearance; it is not exact contour or brushwork retention.", "tags": [ "artist-directed-editing", "structure-control", "image-to-image" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB13", "title": "Paint by Example: Exemplar-based Image Editing with Diffusion Models", "creator": "Binxin Yang and colleagues", "url": "https://github.com/Fantasy-Studio/Paint-by-Example", "sourceType": "paper/project", "year": "2022; CVPR 2023", "checkedDate": "2026-11-03", "access": "open paper and official code with inference examples; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "A source image, region mask and exemplar image become a reference-conditioned inpainting result.", "practicalTakeaway": "The artist supplies where and what visually. An approved motif or material study can communicate changes that are difficult to describe.", "caveat": "The model intentionally transforms exemplars rather than pasting pixels. Original checkpoints and environment require inspection; exact reference fidelity is unproven.", "tags": [ "own-reference-style", "artist-directed-editing", "reference-image", "inpainting" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB14", "title": "SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models", "creator": "Jaerin Lee and colleagues", "url": "https://github.com/ironjr/semantic-draw", "sourceType": "paper/project", "year": "2024; CVPR 2025", "checkedDate": "2026-11-03", "access": "open paper and official code with demos; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "Hand-drawn regions receive separate semantic prompts, producing an evolving raster image through a streaming diffusion pipeline.", "practicalTakeaway": "The artist paints regions and changes their meaning. Promising for testing balances of differently described areas in a composition.", "caveat": "Speed claims depend on published hardware/settings. Model-specific SD1.5, SDXL and SD3 demos are documented; arbitrary-model compatibility was not tested.", "tags": [ "artist-directed-editing", "hands-on-research", "semantic-brushes", "regional-control" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB15", "title": "PromptPaint: Steering Text-to-Image Generation Through Paint Medium-like Interactions", "creator": "John Joon Young Chung and Eytan Adar", "url": "https://github.com/johnr0/PromptPaint", "sourceType": "paper/project", "year": "2023", "checkedDate": "2026-11-03", "access": "open author paper and code; publisher fetch returned 403", "evidence": "opened", "processDepth": "partial", "summary": "Prompt mixtures, stencils and interventions steer different areas and stages of image generation through a paint-inspired interface.", "practicalTakeaway": "The artist mixes concepts and intervenes during generation. Valuable design precedent for gradual exploration rather than a single prompt submission.", "caveat": "Research setup spans local services, Colab and ngrok, possibly paid compute. Interface studies do not establish superiority for abstract painters.", "tags": [ "artist-directed-editing", "co-drawing", "interaction-design", "prompt-mixing" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB16", "title": "Collaborative Neural Painting", "creator": "Nicola Dall’Asen and colleagues", "url": "https://github.com/Fodark/collaborative-neural-painting", "sourceType": "paper/project", "year": "2023; CVIU 2025", "checkedDate": "2026-11-03", "access": "open paper/project and official code; dataset release incomplete", "evidence": "opened", "processDepth": "partial", "summary": "User brushstrokes or an object class condition proposed stroke sequences, allowing iterative editing and composition.", "practicalTakeaway": "The artist can modify individual strokes during completion. Its editable representation is a useful precedent for preserving decisions beyond final raster pixels.", "caveat": "Dataset remains marked Coming soon; checkpoint download is linked but untested. Object-painting research does not demonstrate an arbitrary-archive collaborator. The project page also marks the demo Coming Soon.", "tags": [ "co-drawing", "editable-strokes", "artist-directed-editing", "research-prototype" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB17", "title": "FRIDA: A Collaborative Robot Painter with a Differentiable, Real2Sim2Real Planning Environment", "creator": "Peter Schaldenbrand, James McCann and Jean Oh", "url": "https://pschaldenbrand.github.io/frida/", "sourceType": "paper/project", "year": "2022; ICRA 2023", "checkedDate": "2026-11-03", "access": "open paper/project and shared official robot code; hardware not tested", "evidence": "opened", "processDepth": "detailed", "summary": "Human text, sketch or reference goals become planned brushstrokes, physically executed and revised from camera feedback.", "practicalTakeaway": "The artist supplies goals and material context. It demonstrates a genuine canvas output and the importance of adapting to actual paint behaviour.", "caveat": "Requires robot, camera, calibrated workspace and material setup. A simulator or open repository does not provide a ready studio assistant.", "tags": [ "physical-output", "own-reference-style", "robot-painting", "material-feedback" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB18", "title": "CoFRIDA: Self-Supervised Fine-Tuning for Human-Robot Co-Painting", "creator": "Peter Schaldenbrand and colleagues", "url": "https://pschaldenbrand.github.io/cofrida/", "sourceType": "paper/project", "year": "2024", "checkedDate": "2026-11-03", "access": "open paper/project and shared official robot code; hardware not tested", "evidence": "opened", "processDepth": "detailed", "summary": "A partially painted canvas and text goal guide new robot marks, with a model adapted to physical execution constraints.", "practicalTakeaway": "The person keeps painting and redirecting the collaboration. The project specifically documents human watercolour combined with robot marker work.", "caveat": "Research robot integration requires calibration and compatible materials. Published mixed-media examples do not guarantee preservation of any artist’s existing marks.", "tags": [ "physical-output", "co-drawing", "mixed-media", "robot-painting" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB19", "title": "Diffusion Illusions: Hiding Images in Plain Sight", "creator": "Ryan Burgert and colleagues", "url": "https://diffusionillusions.com/", "sourceType": "paper/project", "year": "2023; SIGGRAPH 2024", "checkedDate": "2026-11-03", "access": "open paper/project, official notebooks and printable examples; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "Chosen prompts or images guide jointly optimized images that reveal different content when flipped, rotated or physically overlaid.", "practicalTakeaway": "The artist chooses paired readings and arrangement. Offers an edition/object route through transparencies, backlighting or hinged tiles.", "caveat": "Illusion constraints can dominate the imagery. Physical alignment, printing and light need trials; examples establish no compatibility with a particular painting practice. Demonstrated overlays use printed overhead sheets and backlighting; transfer to spaced hand-painted glass and coloured wall light is untested.", "tags": [ "physical-output", "mixed-media", "print", "optical-illusion" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "LAB20", "title": "TokenFlow: Consistent Diffusion Features for Consistent Video Editing", "creator": "Michal Geyer, Omer Bar-Tal, Shai Bagon and Tali Dekel", "url": "https://diffusion-tokenflow.github.io/", "sourceType": "paper/project", "year": "2023; ICLR 2024", "checkedDate": "2026-11-03", "access": "open paper, project and official editing code; not executed", "evidence": "opened", "processDepth": "detailed", "summary": "A source video and target prompt become an edited sequence using cross-frame feature correspondence to support consistency.", "practicalTakeaway": "The artist authors source motion and edit intent. An approved filmed brush gesture could become a controlled moving-image study.", "caveat": "Reconstruction quality and the base edit matter; authors note possible decoder jitter. Temporal coherence does not guarantee exact colour, contour or texture retention.", "tags": [ "coherent-video", "artist-directed-editing", "video-to-video", "temporal-consistency" ], "group": "Workflows and papers", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "CTX01", "title": "Understanding and Creating Art with AI: Review and Outlook", "creator": "Eva Cetinic and James She", "url": "https://arxiv.org/abs/2102.09109", "sourceType": "survey paper", "year": "2021 preprint; 2022 journal", "access": "open paper", "processDepth": "partial", "summary": "Reviews both artwork analysis and new-art creation, with a bibliography spanning image collections, aesthetics and generative methods.", "practicalTakeaway": "Use its reference map to locate distinct artistic questions before choosing a model.", "caveat": "Abstract and source record checked; not a current installation manual or proof that every cited method works on these paintings.", "tags": [ "survey", "art analysis", "generative methods" ], "checkedDate": "2026-11-03", "evidence": "opened", "group": "Frameworks and context", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "CTX02", "title": "Designing Creative AI Partners with COFI", "creator": "Jeba Rezwana and Mary Lou Maher", "url": "https://arxiv.org/abs/2204.07666", "sourceType": "interaction research paper", "year": "2022 preprint; 2023 journal", "access": "open paper", "processDepth": "partial", "summary": "A framework for modelling turn-taking, contribution and communication in human–AI creative systems; the authors analyse 92 existing systems.", "practicalTakeaway": "Ask whether the artist can correct, reject, redirect and take turns with the system.", "caveat": "Paper abstract and record checked; the framework is not a validated prediction of Iana's preferences. The authors limit the observed interaction clusters to their historical 92-system dataset.", "tags": [ "co-creation", "human control", "evaluation" ], "checkedDate": "2026-11-03", "evidence": "opened", "group": "Frameworks and context", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "CTX03", "title": "Painting Robot e-David — project and collaborations", "creator": "University of Konstanz Visual Computing", "url": "https://www.cgmi.uni-konstanz.de/en/forschung/e-david/", "sourceType": "institutional process", "year": null, "access": "Full indexed primary project text retrieved through the web reader on 3 November 2026 after an earlier restricted fetch and direct HTTP 404. A separate university collaboration article also opened. Current-origin availability remains uncertain.", "processDepth": "detailed", "summary": "Explains image abstraction into regions/strokes, a paint plan and camera-based feedback while a robot applies real paint. Includes collaborations with Liat Grayver.", "practicalTakeaway": "Study how material limitations, stroke planning and observation change the process of making a painting.", "caveat": "Hardware research platform; no claim this is a downloadable turnkey studio tool. Components include AI-based semantic information and conventional control.", "tags": [ "physical painting", "robotics", "feedback", "artist collaboration" ], "checkedDate": "2026-11-03", "evidence": "opened", "group": "Frameworks and context", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "unverifiable-current-access", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "CTX04", "title": "Wekinator examples", "creator": "Rebecca Fiebrink and contributors", "url": "https://github.com/fiebrink1/wekinator_examples", "sourceType": "official example repository", "year": null, "access": "free code repository", "processDepth": "detailed", "summary": "Input/output examples and teaching examples for interactive machine learning across programming environments.", "practicalTakeaway": "A starting point for learning a relationship between an artist's gestures and a visual or sonic response.", "caveat": "Repository contents checked; dependencies/examples were not installed or executed. Not an image-generation painting model.", "tags": [ "gesture", "interactive machine learning", "teaching", "code" ], "checkedDate": "2026-11-03", "evidence": "opened", "group": "Frameworks and context", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "CTX05", "title": "Machine Learning Education for Artists, Musicians, and Other Creative Practitioners", "creator": "Rebecca Fiebrink", "url": "https://ualresearchonline.arts.ac.uk/id/eprint/15453/1/Fiebrink_TOCE2019_Accepted.pdf", "sourceType": "education research paper", "year": "2019", "access": "free accepted-manuscript PDF", "processDepth": "detailed", "summary": "Describes learning objectives, teaching strategies and evidence from courses for creative practitioners.", "practicalTakeaway": "Learn by building, demonstrating, testing and refining expressive systems, rather than beginning with model metrics alone.", "caveat": "Public PDF opened; historical course studies do not establish present course enrolment or current software compatibility.", "tags": [ "education", "artist learning", "interactive systems" ], "checkedDate": "2026-11-03", "evidence": "opened", "group": "Frameworks and context", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "CTX06", "title": "Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space", "creator": "Jimmy Secretan and colleagues", "url": "https://www.campbellssite.com/papers/secretan_ecj11.pdf", "sourceType": "research paper", "year": "2011", "access": "free author-hosted manuscript PDF", "processDepth": "detailed", "summary": "Documents people selecting, evolving and branching images through collaborative interactive evolution and neuroevolution.", "practicalTakeaway": "An alternative to a single prompt: let artistic preferences guide a branching search through possibilities.", "caveat": "Historical research, not diffusion. The original hosted interface was not tested; an available paper does not establish a working service.", "tags": [ "human selection", "evolutionary art", "collaboration", "historical" ], "checkedDate": "2026-11-03", "evidence": "opened", "group": "Frameworks and context", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "CTX07", "title": "Projects: Technelegy, text works and media-rich poetry", "creator": "Sasha Stiles", "url": "https://www.sashastiles.com/projects", "sourceType": "artist project archive", "year": null, "access": "free artist project pages", "processDepth": "partial", "summary": "Documents AI co-authored poetry alongside text paintings, mixed-media objects and moving-image adaptations.", "practicalTakeaway": "See how an authored text corpus can feed a sustained practice across digital and physical publication.", "caveat": "Adjacent literary/visual practice, not an abstract-painting recipe. Some descriptions are artist statements, not reproducible training instructions.", "tags": [ "poetry", "artist archive", "physical editions", "moving image", "adjacent" ], "checkedDate": "2026-11-03", "evidence": "opened", "group": "Frameworks and context", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } }, { "id": "CTX08", "title": "Association for Computational Creativity — publications and teaching resources", "creator": "Association for Computational Creativity", "url": "https://computationalcreativity.net/", "sourceType": "research discovery archive", "year": null, "access": "free directory and proceedings links", "processDepth": "partial", "summary": "A research hub linking conference proceedings, bibliographies, journals and teaching resources.", "practicalTakeaway": "Use its curated references to extend beyond a fixed list of tools or famous artists.", "caveat": "A discovery portal rather than one production tutorial; homepage event text may be dated. Check individual papers and course availability.", "tags": [ "bibliography", "research archive", "teaching", "discovery" ], "checkedDate": "2026-11-03", "evidence": "opened", "group": "Frameworks and context", "newToEarlierNotes": true, "audit": { "date": "2026-11-03", "verdict": "supported", "scope": "Primary source claims/access reviewed; no code, model, fabrication or optical behavior executed." } } ], "originalCompiledDate": "2026-10-31", "auditSummary": { "recordsReviewed": 67, "verdicts": { "supported": 57, "correction-needed": 3, "partly-supported": 5, "unverifiable-current-access": 2 }, "report": "../research-audit-2026-11-03/README.md", "caveat": "Verdicts describe audit scope; partly-supported records include unretrieved full text. CTX03 primary text was retrieved in a parent follow-up while current-origin access remains uncertain.", "verdictTiming": "Before corrections; the three artist entries have now been corrected. Full-text/current-origin limits remain documented." } }