A is for Adele: An Offline Evaluation Metric for Instant Search
Bibliographic record
Abstract
Instant search has emerged as the dominant search paradigm in entity-focused search applications, including search on Apple Music, Kayak, LinkedIn, and Spotify. Unlike the traditional search paradigm, in which users fully issue their query and then the system performs a retrieval round, instant search delivers a new result page with every keystroke. Despite the increasing prevalence of instant search, evaluation methodologies for instant search have not been fully developed and validated. As a result, we have no established evaluation metrics to measure improvements to instant search, and instant search systems still share offline evaluation metrics with traditional search systems. In this work, we first highlight critical differences between traditional search and instant search from an evaluation perspective. We then consider the difficulties of employing offline evaluation metrics designed for the traditional search paradigm to assess the effectiveness of instant search. Finally, we propose a new offline evaluation metric based on the unique characteristics of instant search. To demonstrate the utility of our metric, we conduct experiments across two very different platforms employing instant search: A commercial audio streaming platform and Wikipedia.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.065 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.007 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.007 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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 source (direct Gemma or distilled Codex), 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".