{"ID":5937690,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T13:11:02.074466024Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04299","arxiv_id":"2607.04299","title":"Cognitive Digital Twins for Self-Aware Channel Estimation","abstract":"Artificial intelligence (AI) and machine learning (ML)-based channel estimators silently degrade when propagation conditions drift from their training distributions. This letter proposes a model-agnostic cognitive digital twin (CDT) framework that combines a variational autoencoder (VAE) with latent activation monitoring to detect distribution drift and autonomously execute \\textsc{continue}, \\textsc{update}, or \\textsc{retire} lifecycle actions without requiring ground-truth channel knowledge. The proposed framework is fully compatible with the AI-native lifecycle management envisioned in 3rd Generation Partnership Project (3GPP). Simulations over various channels demonstrate accurate drift detection and robust channel estimation, consistently outperforming conventional offline-trained deep learning estimators under moderate and severe channel drift.","short_abstract":"Artificial intelligence (AI) and machine learning (ML)-based channel estimators silently degrade when propagation conditions drift from their training distributions. This letter proposes a model-agnostic cognitive digital twin (CDT) framework that combines a variational autoencoder (VAE) with latent activation monitori...","url_abs":"https://arxiv.org/abs/2607.04299","url_pdf":"https://arxiv.org/pdf/2607.04299v1","authors":"[\"Afan Ali\",\"Ali Arshad Nasir\",\"Daniel Benevides da Costa\"]","published":"2026-07-05T13:24:20Z","proceeding":"eess.SP","tasks":"[\"eess.SP\"]","methods":"[\"Variational Autoencoder\"]","has_code":false}