EMMA-AMC v0.1¶
Warning
Pre-implementation. This page describes proposed contracts. Class signatures, parameter types, schema fields, and behavior are subject to change before code lands. Once implementation exists, content here will be regenerated from docstrings or sourced from running tests.
Dataset. EMMA-AMC-v0.1 covers the task, target domain, input, labels, splits, and the download command; this recipe pins only the rfgen configuration. Source. rfgen (primary).
rfgen recipe¶
rfgen commit:
<rfgen-commit>(frozen at release; placeholder until pinned).Emitters: the rfgen
emitter_zoogroup,commsfamily, using the full TorchSig-compatible comms modulation zoo (bpsk,qpsk,16qam,64qam,ofdm, and the rest of the standard set). rfgen composes TorchSig for these modulations; EMMA does not redefine them.Receiver array: 8-element array, single-antenna compatible (the task is single-input single-output, SISO, solvable), via the rfgen
MultiRXConfiggroup. Loaded into ArraySpec at load time.Channel environment(s):
E_URBANandE_RURAL, pinned through the rfgenchannelgroup.Labeler + label extraction: the rfgen
labelgroup records the modulation class; LabelExtractor mapsemitters[].modulationto the classification target.SNR (signal-to-noise ratio) regime: wide SNR sweep drawn from the rfgen
channel.snr_db_range; the OOD (out-of-distribution) fold holds out an unseen SNR regime under theSNR_REGIMEaxis.Sample counts: approximately 200k scenes total.
Splits + seeds:
train/dev/holdoutseed ranges pinned at release; the holdout is a frozen secret seed, never published. OOD axis:SNR_REGIME(unseen SNR regime).
Real-capture counterpart¶
EMMA-REAL-OOD-v0.1 (fidelity reference, not a scored AMC target).
Notes¶
AMC is saturated, single-antenna-solvable, and its publisher states the data has known errata and is not used in its products. It is reported but excluded from the aggregated OOD-avg score. Treating AMC gains as benchmark progress re-imports a saturated task EMMA set out to move beyond.
Matched hyperparameter search collapses apparent model gaps on RadioML; see Hanna and Hussain.
References¶
O’Shea, Roy, and Clancy, “Over-the-Air Deep Learning Based Radio Signal Classification,” IEEE J-STSP 2018. The RadioML 2018 lineage. (verify)
DeepSig, “RadioML datasets,” datasets page (deepsig.ai/datasets). The publisher’s public note that RML2016 has known errata and is not used in DeepSig products. (verify URL)
Hanna and Hussain, “Robust Low-SNR Modulation Classification,” 2026, arXiv:2605.27673. Apparent model gaps collapse under matched hyperparameter search; grounds the saturation. (verify)
TorchSig. The signal-generation library rfgen composes for benchmark-compatible modulations.
See Also¶
Task reference: the
E-ID-AMCcontract and the continuity-column exclusion.Datasets: the dataset registry.
Dataset recipe: the recipe schema this page pins.
Datasets validation: the recipe realism audit.