VERITAS: Training and Test Sets for Wireless Channel Change Detection

VERITAS is a dataset for training and testing a Monitor component in AI-native base station transceiver research. It supports the paper 'VERITAS: Verifying the Performance of AI-native Transceiver Actions in Base-Stations' published in IEEE Transactions on Mobile Computing in 2025. The dataset was authored by Nasim Soltani and is hosted on the Texas Data Repository via Dataverse.

Use Cases

• Training a machine learning model for wireless channel change detection based on the described Monitor component.
• Testing the performance of AI-native transceiver actions in base stations based on the dataset's purpose.
• Benchmarking verification algorithms for 5G network performance based on the research context.
• Reproducing results from the associated IEEE Transactions on Mobile Computing paper.

Strengths

• Dataset is directly linked to a peer-reviewed IEEE publication from 2025.
• Associated code repository is publicly available on GitHub for methodological context.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and data size are unknown, which may limit suitability assessment.

Provenance

Source

Texas Data Repository Harvested Dataverse

Collection Method

Likely generated via simulation or experimental measurements for the associated research.

Time Range

null

Freshness

Last updated 2026-04-27 04:40:44; freshness should be verified.

Geography

null