Deep Learning Relevance: Creating Relevant Information (as Opposed to\n Retrieving it)
Bibliographic record
Abstract
What if Information Retrieval (IR) systems did not just retrieve relevant\ninformation that is stored in their indices, but could also "understand" it and\nsynthesise it into a single document? We present a preliminary study that makes\na first step towards answering this question. Given a query, we train a\nRecurrent Neural Network (RNN) on existing relevant information to that query.\nWe then use the RNN to "deep learn" a single, synthetic, and we assume,\nrelevant document for that query. We design a crowdsourcing experiment to\nassess how relevant the "deep learned" document is, compared to existing\nrelevant documents. Users are shown a query and four wordclouds (of three\nexisting relevant documents and our deep learned synthetic document). The\nsynthetic document is ranked on average most relevant of all.\n
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.008 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.006 |
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".