Literature Review¶
The framework is built on top of and informed by a substantial body of prior art. This page covers the headline references; gap analysis and how each citation flows into a design decision are in Design Decisions.
Headline references¶
Synthetic RF data generation¶
TorchSig (Boegner et al., 2022; v2.1.x at writing):
BaseSignalGenerator,Transform, HDF5 I/O, 60+ comms generators. The substrate we wrap.Sionna (Hoydis et al., 2022): link-level simulation, including
sionna.rt(ray tracing) andsionna.phy.channel(TDL/CDL). Channel backend.WidebandSig53: TorchSig’s wideband multi-emitter dataset; the closest existing dataset to what we produce.
RF foundation models and multimodal¶
RF-GPT: RF + text pairing via deterministic templates plus LLM rewrite. Annotation pattern.
WavCaps (Mei et al., 2024): three-stage audio captioning pipeline (template, bulk LLM, verifier). Pipeline pattern.
Qwen-Audio (Chu et al., 2023): hierarchical-tag conditioning to unify heterogeneous audio label spaces. Taxonomy pattern.
CLIP (Radford et al., 2021): contrastive image-text pretraining. The downstream objective our v2 targets.
Wideband detection and segmentation¶
WRIST (2021): spectrogram-as-image YOLO/DETR detection. Bbox conventions.
ZoomSpec (2026): physics-guided STFT preprocessing for RF detection. STFT default params.
Aboelazm 2025: multi-emitter detection benchmark; scene density realism.
Source datasets we draw from¶
RadioML 2016.10a / 2018.01a, Sig53, HisarMod 2019.1, DroneRF, RFUAV, CardRF, WiSig, SMoRFFI, Daytona ADS-B, NIST CBRS Radar.
Sim-to-real and validation¶
PAES (Physical Attribute Extraction Score): caption quality metric grounded in verifiable physical attributes.
IQFM / LSMs: large signal models; the broader research direction this framework feeds.
Gaps this framework fills¶
Heterogeneous emitter zoo under one interface. TorchSig is comms-only. RadarSimPy, gr-lora_sdr, pyModeS, etc. each ship their own SDK and label conventions. We unify them under BaseEmitter.
Pluggable channel realism. No existing pipeline lets you swap stochastic TDL ↔ ray-traced multipath ↔ hardware impairments by changing one config flag.
Joint labels for the same record. Existing datasets ship bbox or segmentation or per-emitter metadata; no canonical store has all three plus text annotations on the same sample.
Inference-grounded annotations with hallucination control. RF-GPT and WavCaps don’t address hallucination explicitly; we add a verifier subset and JSON-constrained decoding.
Sim-to-real validation harness. Most synthetic RF datasets are pure simulation; ours ships an HIL playback harness on day one.