EMMA-SC-ANOM v1

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-SC-ANOM-v1 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_zoo group. Nominal scenes draw from a known emitter distribution; anomalous scenes inject an out-of-distribution emitter type or behavior. Emitter selection comes from the rfgen scene group.

  • Receiver array: 8-element ULA (uniform linear array), half-wavelength spacing (spacing_lambda: 0.5), via the rfgen MultiRXConfig.geometry member ULA. Loaded into ArraySpec at load time.

  • Channel environment(s): E_URBAN and E_RURAL, pinned through the rfgen channel group.

  • Labeler + label extraction: the rfgen label group records whether a scene contains an anomalous emitter; LabelExtractor maps the anomaly flag to the binary target. The metric is AUROC (area under the ROC curve).

  • SNR (signal-to-noise ratio) regime: drawn from the rfgen channel.snr_db_range.

  • Sample counts: <to be pinned at v1>.

  • Splits + seeds: train / dev / holdout seed ranges pinned at release; the holdout is a frozen secret seed, never published. OOD axis: unseen normal baseline.

Real-capture counterpart

EMMA-REAL-OOD-v0.1 (fidelity reference).

Notes

  • The construct depends on a clean separation between the nominal distribution and the anomaly injection; if the nominal set leaks anomalous examples, AUROC measures memorization, not novelty detection.

  • Class imbalance between nominal and anomalous scenes is expected; AUROC is the threshold-free mitigation.

References

  • Davis and Goadrich, “The relationship between Precision-Recall and ROC curves,” ICML 2006. AUROC grounding. (verify)

  • Ovadia et al., “Can You Trust Your Model’s Uncertainty?,” NeurIPS 2019, arXiv:1906.02530. Predictive uncertainty under dataset shift. (verify)

See Also