Bibliographic record
Abstract
While the World Wide Web (WWW) contains a vast quantity of information, it is often difficult for Web users to find the information they seek. There are many recommender systems that are designed to help users find relevant information on the Web; however, as many of these systems are server-side, they can only provide information about one specific Web site and they are typically based only on correlations amongst the pages that the various users visit. Unfortunately, there is no reason to believe that these correlated pages will necessarily contain useful information. Here, a passive Goal-Directed Complete-Web (GCW) recommender system, which recommends relevant pages from anywhere on the Web to satisfy the user's current information need without any explicit additional input, has been developed. After identifying the search strategy that is employed by actual users while they browse the Web, the model attempts to locate the pages that satisfy the user's information need based on the content of the pages the user has visited, and the actions the user has applied to these pages. To build such models, I develop a number of browsing features ---browsing properties of the words, in the context of the current session---to capture the actions of the Web user. Because the method is based on how the words are used (while training on these browsing feature values), it can be applied to make predictions about pages that have never been visited. This model is therefore independent of users, specific words and specific Web pages, and so it can be used to identify relevant pages in any new Web environment. To evaluate the predictive models, we have conducted two user studies, each involving over one hundred participants. Data from the user studies demonstrate that the models can effectively identify the information needs of new users, leading them to previously unseen, but relevant pages.
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 | 0.001 |
| Open science | 0.001 | 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".