Bibliographic record
Abstract
Authoring is the collection, selection, preparation and presentation of information to one or more readers by an author. The thesis takes a new, critical look at traditional approaches to authoring, by asking what knowledge is required and at which stages of the process. From this perspective, traditional authoring is seen to entrench an early commitment to both form and content. Although the late binding of form is now commonplace in structured document preparation systems, a similar delay in the binding of content is necessary to achieve user-tailored interaction. The authoring paradigm we have developed to service this goal is called intent-based authoring, because the author supplies at compile-time a communicative goal, or intent. Just as SGML editors and HTML browsers defer rendering decisions until run-time by referring to a local stylesheet, intent-based authoring systems defer content-selection decisions until runtime when they refer to models of both author and reader(s). This thesis shows that techniques from artificial intelligence can be developed and used to acquire, represent and exploit such models. Probabilistic abduction is used to recognize user models, and cost-based abduction to design tailored presentations. These techniques are combined in a single framework for best-first recognition and design. These reasoning techniques are further allied with an interaction paradigm we call scrutability, whereby users critique the model in pursuit of better presentations; users see a critical subset of the model determined by sensitivity analysis and can change values through a graphical user interface. The interactivity is modelled to ensure that representations of the user model to the user are made in the most perceptually salient manner. A prototype for intent-based video authoring is described. Video is used as a test medium because it is a "worst case" temporally linear medium; a viable solution to video authoring problems should apply easily to more tractable traditional media. The primary contribution of this dissertation is to the field of applied artificial intelligence, specifically to the emerging field of user modelling. The central contribution is the intent-based authoring framework for separating intent from content.
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 | 0.006 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.012 | 0.003 |
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".