Bibliographic record
Abstract
Abstract Data rescuers worldwide have been trying to retrieve millions of valuable weather historical records so the observations contained in those records are preserved, searchable, analysable and machine readable. The majority of the records are written by hand, in print or cursive handwriting. Automatic transcriptions to date have not been reliable or sufficiently accurate on handwritten data so most of the historical records are transcribed manually. Recent attempts integrate artificial intelligence (AI) to automatically transcribe the historical records but the results have not been promising. Currently there is no end‐to‐end workflow to automatically transcribe historical handwritten tabular records into digital datasets. We propose a workflow that uses AI to automate the handwriting transcription process. The workflow is tested using the historical climate records from the Data Rescue: Archives and Weather (DRAW) project. This workflow is composed of five steps: (1) image pre‐processing, (2) text line segmentation, (3) bounding boxes detection, (4) AI‐enabled optical character recognition (OCR) and (5) layout re‐arrangement. These steps are modular to better accommodate future advances (e.g., new image training data, better layout detectors). We hope the workflow proposed can serve as a guideline that is easily replicable and can be utilized to transcribe other historical datasets.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.007 |
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".