{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SO5NMDH2PVQYN3JGG5L4OLI4F3","short_pith_number":"pith:SO5NMDH2","schema_version":"1.0","canonical_sha256":"93bad60cfa7d6186ed263757c72d1c2ed71933f592a9bca6cf3f9b3ffb18671d","source":{"kind":"arxiv","id":"2301.12798","version":3},"attestation_state":"computed","paper":{"title":"Reliable Federated Disentangling Network for Non-IID Domain Feature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Huazhu Fu, Kai Yu, Ke Zou, Lianyu Wang, Meng Wang, Rick Siow Mong Goh, Yiming Qian, Yong Liu","submitted_at":"2023-01-30T11:46:34Z","abstract_excerpt":"Federated learning (FL), as an effective decentralized distributed learning approach, enables multiple institutions to jointly train a model without sharing their local data. However, the domain feature shift caused by different acquisition devices/clients substantially degrades the performance of the FL model. Furthermore, most existing FL approaches aim to improve accuracy without considering reliability (e.g., confidence or uncertainty). The predictions are thus unreliable when deployed in safety-critical applications. Therefore, aiming at improving the performance of FL in non-Domain featu"},"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":"2301.12798","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-30T11:46:34Z","cross_cats_sorted":[],"title_canon_sha256":"2e99643915cdf28894b171b184747b6ac71cc6bed2c9f5272ab5e8ecd2f88d07","abstract_canon_sha256":"5b127824f34a0fe2934c530f88a30845e2ed463081c562f1d807948cf38aec3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:02.125323Z","signature_b64":"N9qOgRC3IpiaC2scCelGL3lXLBL1rzPbRHEPVvZu9ABmdIkZJMtcfMpKfFPF+Ol5DWGT+KdEGEdMfNQQhyBKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93bad60cfa7d6186ed263757c72d1c2ed71933f592a9bca6cf3f9b3ffb18671d","last_reissued_at":"2026-07-05T06:52:02.124833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:02.124833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliable Federated Disentangling Network for Non-IID Domain Feature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Mei Feng, Huazhu Fu, Kai Yu, Ke Zou, Lianyu Wang, Meng Wang, Rick Siow Mong Goh, Yiming Qian, Yong Liu","submitted_at":"2023-01-30T11:46:34Z","abstract_excerpt":"Federated learning (FL), as an effective decentralized distributed learning approach, enables multiple institutions to jointly train a model without sharing their local data. However, the domain feature shift caused by different acquisition devices/clients substantially degrades the performance of the FL model. Furthermore, most existing FL approaches aim to improve accuracy without considering reliability (e.g., confidence or uncertainty). The predictions are thus unreliable when deployed in safety-critical applications. Therefore, aiming at improving the performance of FL in non-Domain featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12798","kind":"arxiv","version":3},"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/2301.12798/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":"2301.12798","created_at":"2026-07-05T06:52:02.124891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12798v3","created_at":"2026-07-05T06:52:02.124891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12798","created_at":"2026-07-05T06:52:02.124891+00:00"},{"alias_kind":"pith_short_12","alias_value":"SO5NMDH2PVQY","created_at":"2026-07-05T06:52:02.124891+00:00"},{"alias_kind":"pith_short_16","alias_value":"SO5NMDH2PVQYN3JG","created_at":"2026-07-05T06:52:02.124891+00:00"},{"alias_kind":"pith_short_8","alias_value":"SO5NMDH2","created_at":"2026-07-05T06:52:02.124891+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/SO5NMDH2PVQYN3JGG5L4OLI4F3","json":"https://pith.science/pith/SO5NMDH2PVQYN3JGG5L4OLI4F3.json","graph_json":"https://pith.science/api/pith-number/SO5NMDH2PVQYN3JGG5L4OLI4F3/graph.json","events_json":"https://pith.science/api/pith-number/SO5NMDH2PVQYN3JGG5L4OLI4F3/events.json","paper":"https://pith.science/paper/SO5NMDH2"},"agent_actions":{"view_html":"https://pith.science/pith/SO5NMDH2PVQYN3JGG5L4OLI4F3","download_json":"https://pith.science/pith/SO5NMDH2PVQYN3JGG5L4OLI4F3.json","view_paper":"https://pith.science/paper/SO5NMDH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12798&json=true","fetch_graph":"https://pith.science/api/pith-number/SO5NMDH2PVQYN3JGG5L4OLI4F3/graph.json","fetch_events":"https://pith.science/api/pith-number/SO5NMDH2PVQYN3JGG5L4OLI4F3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SO5NMDH2PVQYN3JGG5L4OLI4F3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SO5NMDH2PVQYN3JGG5L4OLI4F3/action/storage_attestation","attest_author":"https://pith.science/pith/SO5NMDH2PVQYN3JGG5L4OLI4F3/action/author_attestation","sign_citation":"https://pith.science/pith/SO5NMDH2PVQYN3JGG5L4OLI4F3/action/citation_signature","submit_replication":"https://pith.science/pith/SO5NMDH2PVQYN3JGG5L4OLI4F3/action/replication_record"}},"created_at":"2026-07-05T06:52:02.124891+00:00","updated_at":"2026-07-05T06:52:02.124891+00:00"}