{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PYCXBZGTOCTBGI6FSJWD5EMWB2","short_pith_number":"pith:PYCXBZGT","schema_version":"1.0","canonical_sha256":"7e0570e4d370a61323c5926c3e91960e8700f341c1ff861e9b1ab2a9710ede9b","source":{"kind":"arxiv","id":"2506.06090","version":1},"attestation_state":"computed","paper":{"title":"Distribution-Level AirComp for Wireless Federated Learning under Data Scarcity and Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.SP","authors_text":"Hyowoon Seo, Jun-pyo Hong, Kisong Lee","submitted_at":"2025-06-06T13:50:22Z","abstract_excerpt":"The conventional FL methods face critical challenges in realistic wireless edge networks, where training data is both limited and heterogeneous, often leading to unstable training and poor generalization. To address these challenges in a principled manner, we propose a novel wireless FL framework grounded in Bayesian inference. By virtue of the Bayesian approach, our framework captures model uncertainty by maintaining distributions over local weights and performs distribution-level aggregation of local distributions into a global distribution. This mitigates local overfitting and client drift,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.06090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2025-06-06T13:50:22Z","cross_cats_sorted":[],"title_canon_sha256":"0a0b94d4490940cb85c84ef7627a586e713f86dcbb78ca90bf307b73be2abcc4","abstract_canon_sha256":"b0b346fe76ff386f9fff720738451f0991a4df220ccb69970be1edf3e43bbe6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:25.466387Z","signature_b64":"NU2ZcUtNVujStwoM/Gwqy8HMLqJCVjCEMtjJ12hGEEwQl1Yu+6JELzD5WPXulEOu/5t0GHNSGbxcwRE4KOG8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e0570e4d370a61323c5926c3e91960e8700f341c1ff861e9b1ab2a9710ede9b","last_reissued_at":"2026-07-05T11:17:25.465895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:25.465895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution-Level AirComp for Wireless Federated Learning under Data Scarcity and Heterogeneity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.SP","authors_text":"Hyowoon Seo, Jun-pyo Hong, Kisong Lee","submitted_at":"2025-06-06T13:50:22Z","abstract_excerpt":"The conventional FL methods face critical challenges in realistic wireless edge networks, where training data is both limited and heterogeneous, often leading to unstable training and poor generalization. To address these challenges in a principled manner, we propose a novel wireless FL framework grounded in Bayesian inference. By virtue of the Bayesian approach, our framework captures model uncertainty by maintaining distributions over local weights and performs distribution-level aggregation of local distributions into a global distribution. This mitigates local overfitting and client drift,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06090","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.06090/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.06090","created_at":"2026-07-05T11:17:25.465951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06090v1","created_at":"2026-07-05T11:17:25.465951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06090","created_at":"2026-07-05T11:17:25.465951+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYCXBZGTOCTB","created_at":"2026-07-05T11:17:25.465951+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYCXBZGTOCTBGI6F","created_at":"2026-07-05T11:17:25.465951+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYCXBZGT","created_at":"2026-07-05T11:17:25.465951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYCXBZGTOCTBGI6FSJWD5EMWB2","json":"https://pith.science/pith/PYCXBZGTOCTBGI6FSJWD5EMWB2.json","graph_json":"https://pith.science/api/pith-number/PYCXBZGTOCTBGI6FSJWD5EMWB2/graph.json","events_json":"https://pith.science/api/pith-number/PYCXBZGTOCTBGI6FSJWD5EMWB2/events.json","paper":"https://pith.science/paper/PYCXBZGT"},"agent_actions":{"view_html":"https://pith.science/pith/PYCXBZGTOCTBGI6FSJWD5EMWB2","download_json":"https://pith.science/pith/PYCXBZGTOCTBGI6FSJWD5EMWB2.json","view_paper":"https://pith.science/paper/PYCXBZGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06090&json=true","fetch_graph":"https://pith.science/api/pith-number/PYCXBZGTOCTBGI6FSJWD5EMWB2/graph.json","fetch_events":"https://pith.science/api/pith-number/PYCXBZGTOCTBGI6FSJWD5EMWB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYCXBZGTOCTBGI6FSJWD5EMWB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYCXBZGTOCTBGI6FSJWD5EMWB2/action/storage_attestation","attest_author":"https://pith.science/pith/PYCXBZGTOCTBGI6FSJWD5EMWB2/action/author_attestation","sign_citation":"https://pith.science/pith/PYCXBZGTOCTBGI6FSJWD5EMWB2/action/citation_signature","submit_replication":"https://pith.science/pith/PYCXBZGTOCTBGI6FSJWD5EMWB2/action/replication_record"}},"created_at":"2026-07-05T11:17:25.465951+00:00","updated_at":"2026-07-05T11:17:25.465951+00:00"}