Bibliographic record
Abstract
Cranfield-style information retrieval evaluation considers variance in user information needs by evaluating retrieval systems over a set of search topics. For each search topic, traditional metrics model all users searching ranked lists in exactly the same manner and thus have zero variance in their per-topic estimate of effectiveness. Metrics that fail to model user variance overestimate the effect size of differences between retrieval systems. The modeling of user variance is critical to understanding the impact of effectiveness differences on the actual user experience. If the variance of a difference is high, the effect on user experience will be low. Time-biased gain is an evaluation metric that models user interaction with ranked lists that are displayed using document surrogates. In this paper, we extend the stochastic simulation of time-biased gain to model the variation between users. We validate this new version of time-biased gain by showing that it produces distributions of gain that agree well with actual distributions produced by real users. With a per-topic variance in its effectiveness measure, time-biased gain allows for the measurement of the effect size of differences, which allows researchers to understand the extent to which predicted performance improvements matter to real users.
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 | 0.013 | 0.087 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".