Tracking Visual Differences for Generation and Playback of User-Customized Notifications
Bibliographic record
Abstract
Notification systems alert individuals or groups of changing information that is of interest to them. The problem is that it is difficult for people to gather notifications of personal interest; they must either rely on the generic offerings of the information provider, or construct their own services through coding. In this paper, we contribute a simple yet effective method that lets people create custom notification elements by image assembly, where notifications are triggered through visual differencing. First, after finding information of interest on a web page, the person constructs a visual collage selected from regions on the page. These are regions of the fully rendered bitmap view of the page i.e., they are not coupled to the page s underlying HTML markup. The composite image created from this collage will be used to assemble a notification of relevant changes to that web page. Second, the person specifies one or more regions on the page that will be compared for visual differences over time, and how often the page should be revisited to check for these differences. The system will automatically generate a notification (the composite image plus a title and timestamp) when differences go beyond a user provided threshold. Finally, the person can view the notifications in several ways: as only the most recently changed version (to illustrate current state), or as an image history that can be either browsed individually or played back as a continuous video stream (to see changes over time).
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 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 | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".