Response to the Letter to the Editor—Appealing abstracts: ChatGPT or outside advice?
Bibliographic record
Abstract
We thank Dr. Shigeki Matsubara for his insightful comments on our recent article published in Paediatrics & Child Health (1). Dr. Matsubara raised two key considerations. First, he noted that the improvements observed in our study may not be unique to ChatGPT but could equally result from advice provided by another reader. We agree. Our study was not designed to compare ChatGPT with human reviewers but rather to evaluate whether ChatGPT could serve as an accessible form of external review. Our findings showed that when researchers believed their abstract was ready for submission, asking ChatGPT to improve it was associated with measurable improvement in quality. We interpret this not as evidence that ChatGPT is superior to human input, but as support for its potential role as an immediately available and low-barrier source of external feedback. Second, Dr. Matsubara suggested that improvements might reflect the benefit of re-reading an abstract after a delay. We acknowledge this possibility and explicitly discussed it as a limitation. However, participants were asked to provide what they considered their final version before ChatGPT's revision. Abstracts were returned within 24 hours, and all final versions were completed within 48 hours, limiting the influence of delayed self-review alone. Moreover, 75% of participants explicitly reported that ChatGPT helped improve their abstracts, supporting the interpretation that its input contributed meaningfully to refinement.
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 | 0.004 | 0.047 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.005 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.045 | 0.040 |
| Insufficient payload (model declined to judge) | 0.025 | 0.020 |
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".