User Task Adaptation in Multimedia Presentations.
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
It is quite common that documents ranging from newspaper articles to scientific papers convey complex information by combining visualizations with textual material. Presenting information in different modalities not only makes the presentation more engaging, but could also better suit users with different cognitive skills (visual vs. verbal). In these multimedia presentations graphics and text play complementary roles. While graphics can convey large amounts of data compactly and support discovery of trends and relationships, text is much more effective at pointing out and explaining key points about the data, in particular by focusing on specific temporal, causal and evaluative aspects [1]. For illustration, Figure 1 shows an example of a multimedia presentation from The Economist magazine. Notice, for instance, how the sentence “The end of subsidies to car buyers will lead to a slump in Japan, just as its carmakers’ output recovers from the 2011 tsunami.” provides a causal explanation for the noticeably extreme data about current (year 2012) and forecasted (year 2013) car sales in Japan. Generally speaking, the textual part of a multimedia presentation can be seen as suggesting to the reader a set of visual tasks that can be performed by inspecting the visualization. For example, when reading the two sentences “India and China will have further strong rises—though not at the double-digit rates seen until 2010. Brazil and Britain will suffer reverses.” the reader is prompted to verify in the visualization (the deviation chart) that all the bars for India and China are on the right side of the chart (i.e., sales are increasing) and less than 10%, while the bars for Brazil and Britain are on the right for 2012, but on the left side (i.e., sales are decreasing) for the 2013 forecast.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it