{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B2AUAALRR7UN4OQSHMCD2KZLB7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bb95b688faa67b03fcbf97a8c46d36dc71a868ad7feb2d553ccb38d0799fd63e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SP","submitted_at":"2026-05-06T09:25:19Z","title_canon_sha256":"3d40d37ba1e4e4d69238bacf3fa00e2772cb227c2dde8f0191998ff7ec92dfa7"},"schema_version":"1.0","source":{"id":"2605.04676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04676","created_at":"2026-06-22T11:44:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04676v1","created_at":"2026-06-22T11:44:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04676","created_at":"2026-06-22T11:44:46Z"},{"alias_kind":"pith_short_12","alias_value":"B2AUAALRR7UN","created_at":"2026-06-22T11:44:46Z"},{"alias_kind":"pith_short_16","alias_value":"B2AUAALRR7UN4OQS","created_at":"2026-06-22T11:44:46Z"},{"alias_kind":"pith_short_8","alias_value":"B2AUAALR","created_at":"2026-06-22T11:44:46Z"}],"graph_snapshots":[{"event_id":"sha256:31e75e0e0428d4f2f32732e7351b405bb2d2d7c58f23e80d8c4d410aea2adcd7","target":"graph","created_at":"2026-06-22T11:44:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":1,"snapshot_sha256":"5e3b23b793a24ad44d50f012bed3c12f7c9e9c566d826ad85b79440943422c6c","strong_count":1},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"VLMs trained on synthetic spectrogram data can generalize to real RF environments, particularly for extracting physical signal attributes such as spectral occupancy, temporal behavior, and SNR. This indicates that synthetic data is sufficient for learning transferable representations of RF signal structure."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The synthetic training data distribution is representative enough of real over-the-air RF variations to support generalization, especially outside the low-SNR regimes explicitly noted as failure cases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VLMs trained on synthetic RF spectrograms generalize to real signals for physical attribute extraction but lack reliable semantic grounding without additional priors."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Vision-language models can learn to understand real RF signals from synthetic spectrogram data alone."}],"snapshot_sha256":"2ee1bf4c3175bb90b6fcd6647570c94381cc235db3c757319cee82b07f94b623"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T11:35:51.692647Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.810994Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T14:14:35.364583Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.04676/integrity.json","findings":[],"snapshot_sha256":"8be7b043cfc2a8deb2eb3c06110c0aa6043188f4ff70e1bac403601d4e1c7085","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the wireless spectrum is a fundamen- tal requirement for intelligent communication systems, however, interpreting spectrograms requires extracting multiple physical attributes and reasoning about signal structure, which is a capability that is not achieved by traditional ML approaches. Recent advances in vision-language models (VLMs) demonstrated the possibility of learning such interpretation capabilities directly from data. This paper investigates whether VLMs can learn this capability from synthetic data alone, and more importantly, whether such learned representations general","authors_text":"Anis Bara, Brahim Mefgouda, Hang Zou, Lina Bariah, Merouane Debbah","cross_cats":[],"headline":"Vision-language models can learn to understand real RF signals from synthetic spectrogram data alone.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SP","submitted_at":"2026-05-06T09:25:19Z","title":"RF-Analyzer: Can Vision-Language Models Learn RF Understanding from Synthetic Data?"},"references":{"count":12,"internal_anchors":0,"resolved_work":12,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Large generative AI models for telecom: The next big thing?","work_id":"f8750689-e00c-482a-9d5f-10c2d509cd57","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"TelecomGPT: A framework to build telecom-specific large language models","work_id":"24ded6c4-f52f-438b-9af2-a37f3aae28ee","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Large language model (LLM) for telecommunications: A comprehensive survey on principles, key techniques, and opportunities","work_id":"6fb0e76e-1834-4f64-801c-6cc67bdd84f8","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Spectrum analyzers and signal analyz- ers","work_id":"3810a063-a2c9-4822-9761-377ba3d41e33","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Signal analyzers","work_id":"0bc1b7d1-a4bb-42b8-b652-63b584295c08","year":2024}],"snapshot_sha256":"df5c04025d55cfe81f1f690dee348dedba106eb0c1f25bf45f8010499ca07287"},"source":{"id":"2605.04676","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-08T16:46:56.717793Z","id":"b1ac989b-9b78-426b-8cbf-73dae53c0294","model_set":{"reader":"grok-4.3"},"one_line_summary":"VLMs trained on synthetic RF spectrograms generalize to real signals for physical attribute extraction but lack reliable semantic grounding without additional priors.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Vision-language models can learn to understand real RF signals from synthetic spectrogram data alone.","strongest_claim":"VLMs trained on synthetic spectrogram data can generalize to real RF environments, particularly for extracting physical signal attributes such as spectral occupancy, temporal behavior, and SNR. This indicates that synthetic data is sufficient for learning transferable representations of RF signal structure.","weakest_assumption":"The synthetic training data distribution is representative enough of real over-the-air RF variations to support generalization, especially outside the low-SNR regimes explicitly noted as failure cases."}},"verdict_id":"b1ac989b-9b78-426b-8cbf-73dae53c0294"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0144f9aa8b0671808fdd454544a933f8a7bceb8b9715daca5517b4b06de10cc2","target":"record","created_at":"2026-06-22T11:44:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bb95b688faa67b03fcbf97a8c46d36dc71a868ad7feb2d553ccb38d0799fd63e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SP","submitted_at":"2026-05-06T09:25:19Z","title_canon_sha256":"3d40d37ba1e4e4d69238bacf3fa00e2772cb227c2dde8f0191998ff7ec92dfa7"},"schema_version":"1.0","source":{"id":"2605.04676","kind":"arxiv","version":1}},"canonical_sha256":"0e814001718fe8de3a123b043d2b2b0ff5f66286d3c8841de515621bf359e5cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e814001718fe8de3a123b043d2b2b0ff5f66286d3c8841de515621bf359e5cc","first_computed_at":"2026-06-22T11:44:46.500069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-22T11:44:46.500069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F78iRwzJEKEkw5wSOTcyf6rqYRe4EgUHim1Z2Zf74en76F2BxuBpyt6TjKBq757jeKH+TsbrNOO2Isd3Kt0eDg==","signature_status":"signed_v1","signed_at":"2026-06-22T11:44:46.500554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.04676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0144f9aa8b0671808fdd454544a933f8a7bceb8b9715daca5517b4b06de10cc2","sha256:31e75e0e0428d4f2f32732e7351b405bb2d2d7c58f23e80d8c4d410aea2adcd7"],"state_sha256":"d705ab2bde5dc869cc79bb9412e13044db8833d18ef1b1b0d70d8a6f0f6fc260"}