{
  "abstract": "Deep learning for radio frequency (RF) signal analysis relies on large annotated datasets, yet synthetic datasets trade physical realism for controllability, while uncontrolled over-theair measurements offer realism but limited reproducibility. We present CorteXforge, a scenario-based framework for generating realistic and reproducible RF datasets on programmable software defined radio (SDR) testbeds. High-level RF scenarios are automatically translated into synchronized experiments executed on the SLICES-RI/CorteXlab platform, producing fully annotated Signal Metadata Format (SIGMF) datasets that capture hardware impairments and propagation effects. We validate CorteXforge through automatic modulation classification using ModForge, an over-the-air (OTA) dataset generated with the framework. Cross-domain experiments reveal a synthetic-to-real performance gap and show that synthetic pretraining remains beneficial for adaptation to OTA data. CorteXforge provides a practical foundation for reproducible RF dataset generation and future research on domain generalization.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.26999",
  "author_total": 3,
  "authors": [
    {
      "name": "Andréa Joly"
    },
    {
      "name": "Leonardo S Cardoso"
    },
    {
      "name": "Jean-Marie Gorce"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dk50zh8d1kt3y.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.26999",
  "fulltext_url": null,
  "id": "dk50zh8d1kt3y",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.26999",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.IT"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "math.IT"
    ],
    [
      "openalex",
      "1702|Wireless Signal Modulation Classification"
    ]
  ],
  "openalex": "W7223077834",
  "pdf_url": "https://arxiv.org/pdf/2610.26999",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dk50zh8d1kt3y.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:34:08Z",
      "native_id": "2610.26999",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.26999"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.IT",
      "subfield": "general"
    }
  ],
  "title": "CorteXforge: Scenario-Based RF Dataset Generation on Real Testbeds",
  "title_text": "CorteXforge: Scenario-Based RF Dataset Generation on Real Testbeds",
  "type": "preprint",
  "updated_at": "2026-10-30T12:34:08Z",
  "url": "https://research.draconitic.com/paper/dk50zh8d1kt3y",
  "venue": "arXiv",
  "versions": []
}