Bibliographic record
Abstract
CATMuS (Consistent Approach to Transcribing ManuScript) Medieval is a Kraken HTR model trained on four different languages (in descending order of importance in the dataset: Old and Middle French, Latin, Spanish (and other languages of Spain), Italian) on strictly graphematic transcriptions. No abbreviations are resolved. This model is the result of the collaboration from researchers from CREMMA, GalliCorpora, HTRomance and DEEDS projects. It follows the CREMMA Guidelines (Supplemented by the CREMMA Medii Aevi) and will be consolidated under the CATMuS Medieval Guidelines in an upcoming paper. The model is trained with NFD Unicode normalization: each diacritic (including superscripts) are transcribed as their own characters, separately from the "main" character. Metrics 3,361,410 characters 113,228 lines 1602 files (indifferently double pages or single pages) 7560 regions All source datasets and papers are referenced in the related works section, all transcribers are mentioned in the collaborators section, all partner-project members are mentioned as authors. Fundings CREMMA, DIM MAP, Région Île-de-France CremmaLab, DIM MAP, Région Île-de-France GalliCorpora, Datalab, Bibliothèque nationale de France HTRomance, Datalab, Bibliothèque nationale de France Text as Image, Image as Text: Charter integrity and topic modelling, SSHRCC 1350911 Les Décades de Bersuire, première traduction française de l'Histoire romaine de Tite-Live – LiBer, ANR 21-CE27-0008 Projet Fabliaux, Biblissima+, ANR 21-ESRE-0005
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 | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.063 | 0.073 |
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".