This is a monolingual continued-pretraining control checkpoint reported in the paper table. It is provided for reproducibility of the baseline comparison.

Paper name: PT-Base-CP
Model role: baseline-control
Source/base model: unicamp-dl/ptt5-base-portuguese-vocab
Code and pipeline: GitHub repository
Architecture: T5 encoder-decoder
SciLaD dataset: scilons/SciLaD-all-text-v1
Evaluation benchmark: Global-MMLU

Evaluation

Zero-shot Global-MMLU accuracy reported by the paper aggregation:

Metric	Accuracy
Average	23.02
STEM	21.54
Humanities	24.08
Social Sciences	21.84
Other	24.07

Limitations

The model is evaluated primarily with zero-shot Global-MMLU. Downstream task-specific evaluation is recommended before deployment in specialized scientific workflows.

Citation

Title: Transferring Scientific English Pre-Trained Language Models to Multiple Languages Using Cross-Lingual Transfer
Authors: Nikolas Rauscher, Fabio Barth, Georg Rehm
Venue: LREC-COLING 2026, citation details TBA after publication

rausch/pt-t5-base-sci-cp-15k

PT-Base-CP

Model Details

Evaluation

Limitations

Citation

rausch/
pt-t5-base-sci-cp-15k