Information discovery within organizations using the Athens system
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
The serendipitous discovery of novel information in the web is a challenging task. Existing retrieval tools, like search engines, can retrieve information about known topics. However, they cannot retrieve information about novel topics, that is topics whose existence is unknown to the user and which may be potentially interesting. We present Athens, a system for discovering novel information in the web. Athens comprises three fundamental components: closure to find the essential content of a set of search query terms; probing to create new contextualized queries for retrieving information of wider scope; and clustering to remove less relevant information. Given a set of initial query terms, the system repeats these steps twice to reach novel information relative to the initial query topic. This paper describes an application of the Athens system to web-based data for two organizations: IBM and Microsoft. We compare the novel information generated for the two organizations against a query and discuss the encouraging results obtained.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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