Metadata Extraction and Citation Automation (MECA)
Bibliographic record
Abstract
Zotero is a tool that researchers typically use to manage their articles and import citations. An issue arises when migrating a local database to Zotero. If a bulk import is used, Zotero neither validates nor formats the metadata, which leads to inconsistency (e.g., inconsistent title capitalization and field entries); Otherwise, the data has to be manually reviewed and entered, which can be particularly time-consuming. To address these issues MECA (Metadata Extraction and Citation Automation) is being developed to automate the process and enforce consistency. The program accomplishes this by using optical character recognition or a PDF reader to extract a DOI, which is then validated using a CrossRef API. Upon validation, a predefined set of fields is requested and formatted by identifying nouns through parts-of-speech tagging. The data is then packaged with the corresponding file and inputted into Zotero through an API. Articles that fail any step are skipped and copied into a folder for manual review. The advantage of such automation is that it can enforce consistency, increase efficiency, and operate in the background. The user will only need to review a small subset of the original files that were too ambiguous for the program. The program performs best with newer articles in text-PDF and has a numerical DOI. We are excited by the potential for this project to save scholars in Canada and abroad substantial time citing their research, allowing them to devote their efforts to the pursuit of important scholarly objectives outlined in the SDG.
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 | 0.017 | 0.068 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.025 | 0.021 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.008 | 0.010 |
| Open science | 0.002 | 0.008 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.065 | 0.053 |
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".