Method overview
A synthetically pretrained time series in-context classifier with scalable label encoding.
Evaluated configurations
Native in-context inference
Classifier heads are grouped on this page under their shared pretrained model. They remain separate leaderboard entries because they represent different experimental configurations.
- Organization
- Visa Research
- Parameters
- 47M (TiCT-Large, ResNet)
- Checkpoint used
- No standalone checkpoint link found
- Input Type
- Univariate time series
- Inference
- Training-free in-context classification
Reading this model's evaluation
The method catalog describes the pretrained model; leaderboard eligibility depends on the actual coverage of each experimental configuration. Catalog inclusion does not imply complete coverage of all 198 datasets.