# RASD Laya track classifier decision model by Galal Ban Amr

> RASD Laya classifies synthetic sensor-track descriptions into four labels. Its reported test scores cover one simulator, with no real-airspace validation.

Updated 2026-11-12 (Australia/Adelaide)

## Quick answers

### What is RASD Laya track classifier by Galal Ban Amr?

[RASD Laya track classifier](<https://decisionmodels.ai/models/rasd-laya>): A [Laya](<https://decisionmodels.ai/models/laya>) fine-tune that labels English descriptions of simulated sensor tracks as drone, bird, aircraft or unknown.

[RASD Laya track classifier facts](<https://decisionmodels.ai/models/rasd-laya>)

[Source](<https://huggingface.co/Galal123/rasd-laya-track-classifier>)

### Who makes RASD Laya track classifier?

[RASD Laya track classifier](<https://decisionmodels.ai/models/rasd-laya>): Galal Ban Amr

[RASD Laya track classifier facts](<https://decisionmodels.ai/models/rasd-laya>)

[Source](<https://huggingface.co/Galal123/rasd-laya-track-classifier>)

### Are RASD Laya track classifier's weights open?

[RASD Laya track classifier](<https://decisionmodels.ai/models/rasd-laya>): Public weights, question file and [Laya](<https://decisionmodels.ai/models/laya>) loading example Licence: Apache-2.0 model card

[RASD Laya track classifier facts](<https://decisionmodels.ai/models/rasd-laya>)

[Source](<https://huggingface.co/Galal123/rasd-laya-track-classifier>)

By Galal Ban Amr · Selected weights upload: 2026-11-07 · OPEN

A [Laya](<https://decisionmodels.ai/models/laya>) fine-tune that labels English descriptions of simulated sensor tracks as drone, bird, aircraft or unknown. It classifies only, with no flight-control or engagement outputs. Training and testing use the same simulator with separate runs; the results say nothing about real sensors or airspace.

## Facts

- Base: convaiinnovations/laya, ModernBERT-large
- Inputs: English text in the synthetic dataset's fixed track format
- Training: 10,814 rows, two epochs, soft cross-entropy; run-D selected on validation macro-F1
- Licence: Apache-2.0 model card
- Access: Public weights, question file and [Laya](<https://decisionmodels.ai/models/laya>) loading example

## Claims and sources

- **VENDOR-REPORTED**: The maker reports accuracy 0.956, macro-F1 0.903 and 15-bin ECE 0.005 on 23,358 synthetic test rows from held-out simulation runs. The rule baseline scores 0.386 accuracy and abstains as unknown when evidence is thin, which the test counts as wrong for a real object. Fine-tuned unknown-class precision is 0.571. These results measure generalisation within one simulator. [source](<https://huggingface.co/Galal123/rasd-laya-track-classifier>)

## Links

- [Source: Model card and weights](<https://huggingface.co/Galal123/rasd-laya-track-classifier>)
- [Source: Recorded metrics](<https://huggingface.co/Galal123/rasd-laya-track-classifier/raw/main/metrics.json>)
- [Source: Synthetic dataset](<https://huggingface.co/datasets/Galal123/rasd-tracks-synthetic>)

## Related projects

No related projects are listed in the registry.