Bibliographic record
Abstract
City films or city symphonies have been at the forefront for exploring and combing aesthetic, film process and storytelling, thus a great case for AI experimentation. With the emergence of AI digital content production applications (or Generative Artificial Intelligence - G.A.I.) such as image-based creations (Midjourney, Adobe Firefly) new opportunities for experimental filmmaking and screen production surface. The creative treatment of actuality requires a rethinking as we are now working with artificial or data source material and no longer recorded actualities. MEL 23:55 is an Experiment in AI image generation using Adobe Firefly and Midjourney for the visuals, which are in turn synched with AI audioscape produced with Melobytes. The research objectives was to explore the creative process when using GAI for city film production. An interesting observation is that Google image search does not recognise AI images locations. The city of Melbourne is referenced as being in Germany, Belgium or is referenced as Perth. The theoretical framework is underpinned by an examination of the city symphony phenomenon (Kinik, Hielscher and Jacobs 2018) and leveraging a recent formation of computational non-fiction. The city film is a documentary genre, that is also referred to as a city symphony while, also being described as a phenomenon (Jacobs, Hielscher and Kinik 2018). As a documentary format it facilitates exploration of cinematic language, visual grammar and non-fiction storytelling. There are numerous key-works across the 20th and 21st century, ranging from the Man With a Movie Camera Человек с кино-аппаратом (Chelovek s kino-apparatom) to Koyaanisqatsi. These city films are described as film events, cinematic experiences and experiments in cinematic communication. For Vertov the camera eye had mechanical augmentation; “I am kino-eye, I am mechanical eye. I, a machine shows you the world as only I can see it” (Vertov in Michelson 1984, 15). Reggio described his film experience as “until now, you’re never really seen the world you live in” (Reggio 1982). Could we prose an AI eye, and explore a computational vision of the world? City films or city symphonies have been at the forefront for exploring and combing aesthetic, film process and storytelling, thus a great case for AI experimentation. 21th century logic of documentary and explore emerging computational nonfiction (Miles 2017) formations. Recent literature proposes that non-human systems can become participative agents in the documentary production (Zimmerman 2017 and 2019, Cizek and Uricchio 2022, Kapur and Ansari 2022 among others) The research applies a Creative Practice Research approach (Batty and Kerrigan 2019, MCNamara 2012, Kerrigan and Callaghan 2016). Schleser has had an interest in the city film since his 2008 mobile feature film Max with a Keitai and is experimenting with AI, as an accessible production tool, in the making of a city film. Schleser has worked in alternative documentary traditions by combining Kinoks (Vertov in Michelson 1984), Cinéma Vertié and smartphone filmmaking approaches (Schleser 2021) and hopes to leverage this research approach into the GAI domain.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.005 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.899 | 0.812 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".