EMMA-S2T-CAP v2

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-S2T-CAP-v2 covers the task, target domain, input, labels, splits, and the download command; this recipe pins only the rfgen configuration. Source. rfgen plus the rfgen annotator (Phase 2 captions from a large language model, LLM).

rfgen recipe

  • rfgen commit: <rfgen-commit> (frozen at release; placeholder until pinned).

  • Emitters: the rfgen emitter_zoo group, a heterogeneous mix so captions describe varied scene content.

  • 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 annotator group (AnnotatorConfig with AnnotationType.CAPTION) generates scene captions in Phase 2; LabelExtractor maps the stored caption to the target. Metrics are BLEU (Bilingual Evaluation Understudy), METEOR (Metric for Evaluation of Translation with Explicit ORdering), and CIDEr (Consensus-based Image Description Evaluation).

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

  • Sample counts: <to be pinned at v2>.

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

Real-capture counterpart

None. Captioning is a frontier task with no real-capture counterpart in the EMMA-REAL-OOD set.

Notes

  • (depends on rfgen annotator not yet shipped) This recipe cannot pin until rfgen’s Phase 2 annotator produces verified scene captions at scale. Caption quality is bounded by the bulk and verifier LLMs pinned in the rfgen AnnotatorConfig; the recipe inherits that dependency. Do not treat the recipe as complete until the annotator lands.

  • Ships at v2, after the inner ring (communications, spectrum, drone-RF) is proven. No community does RF captioning at scale today.

  • Tokenization of RF captions is the open task-side choice for the BLEU / METEOR / CIDEr metrics.

References

  • Papineni et al., “BLEU: a Method for Automatic Evaluation of Machine Translation,” ACL 2002. The BLEU captioning metric.

  • Banerjee and Lavie, “METEOR: An Automatic Metric for MT Evaluation,” ACL 2005. (verify)

  • Vedantam et al., “CIDEr: Consensus-based Image Description Evaluation,” CVPR 2015. (verify)

  • Debbah and the MBZUAI group, “RF-GPT,” 2026, arXiv:2602.14833. Spectrogram-based RF-language model; the closest existing analog. (verify)

See Also