Bibliographic record
Abstract
We appreciate Pereira and Castilho's interest (1) in our paper (2), and we agree wholeheartedly with their description of confidence intervals. We wish to address a number of issues regarding our paper and their letter. First, we believe that we made a clerical error in reporting the confidence interval in the paper (2). The interval, calculated as we described in the paper, should be (14.4, 25.5), not (15.6, 24.6) as reported. We would like to elaborate on the points made by Pereira and Castilho (1). In the example cited on page 1204 of our paper (2), we intentionally and carefully chose our words (“representing the 95% probability for the sampling interval”) to indicate that we were describing the sampling distribution of the observed sample proportion, rather than the commonly used confidence interval for the unobserved population proportion. For example, under the theoretical assumption that the true prevalence of diabetes is 0.20, there is a 95% chance that, in a sample of 200, the sample (or observed) prevalence will lie between 0.144 and 0.255. The probability of 95% for the sampling interval is to be distinguished from the usual 95% confidence level. The 95% sampling interval is based on a fixed and known true prevalence, and if we were to repeat the same study with the same design many times, we would expect 95% of these sample prevalences to fall within the specified range. On the other hand, the 95% confidence interval is based on the observed sample, and if we repeated the same study many times, we would expect the confidence intervals of the individual studies to contain the true unknown prevalence 95% of the time.
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 | 0.104 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.005 | 0.003 |
| Scholarly communication | 0.006 | 0.004 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.036 | 0.040 |
| Insufficient payload (model declined to judge) | 0.028 | 0.019 |
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".