{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4PJLP4UV4S4TJI4MV7MMFVTM3I","short_pith_number":"pith:4PJLP4UV","schema_version":"1.0","canonical_sha256":"e3d2b7f295e4b934a38cafd8c2d66cda1a1246e13f12f1c4e88b5cd28912b822","source":{"kind":"arxiv","id":"2210.15865","version":1},"attestation_state":"computed","paper":{"title":"Completely Heterogeneous Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chang Liu, Hongtao Lu, Xun Cai, Yue Ding, Yuwen Yang","submitted_at":"2022-10-28T03:20:10Z","abstract_excerpt":"Federated learning (FL) faces three major difficulties: cross-domain, heterogeneous models, and non-i.i.d. labels scenarios. Existing FL methods fail to handle the above three constraints at the same time, and the level of privacy protection needs to be lowered (e.g., the model architecture and data category distribution can be shared). In this work, we propose the challenging \"completely heterogeneous\" scenario in FL, which refers to that each client will not expose any private information including feature space, model architecture, and label distribution. We then devise an FL framework base"},"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":"2210.15865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-28T03:20:10Z","cross_cats_sorted":["cs.CR","cs.DC"],"title_canon_sha256":"4b1bae47eb427314786a5ec3b7cfdd3841a3faead076540cb04e24f0919d92ee","abstract_canon_sha256":"d37a8df3c1a6e0dacaeabcb7f1c9ee3a8654746d27b73235d22e00e2524f62cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:26.695080Z","signature_b64":"0vkMT8+xkv1pCe4jZjIa5h0OPJCC09pFbxIwW42PyOSyYXdcgeClpY56YjlcW+eBRhE+OgwDbxiNnqYqfbsLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3d2b7f295e4b934a38cafd8c2d66cda1a1246e13f12f1c4e88b5cd28912b822","last_reissued_at":"2026-07-05T05:11:26.694647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:26.694647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Completely Heterogeneous Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Chang Liu, Hongtao Lu, Xun Cai, Yue Ding, Yuwen Yang","submitted_at":"2022-10-28T03:20:10Z","abstract_excerpt":"Federated learning (FL) faces three major difficulties: cross-domain, heterogeneous models, and non-i.i.d. labels scenarios. Existing FL methods fail to handle the above three constraints at the same time, and the level of privacy protection needs to be lowered (e.g., the model architecture and data category distribution can be shared). In this work, we propose the challenging \"completely heterogeneous\" scenario in FL, which refers to that each client will not expose any private information including feature space, model architecture, and label distribution. We then devise an FL framework base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15865","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/2210.15865/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":"2210.15865","created_at":"2026-07-05T05:11:26.694715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15865v1","created_at":"2026-07-05T05:11:26.694715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15865","created_at":"2026-07-05T05:11:26.694715+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PJLP4UV4S4T","created_at":"2026-07-05T05:11:26.694715+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PJLP4UV4S4TJI4M","created_at":"2026-07-05T05:11:26.694715+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PJLP4UV","created_at":"2026-07-05T05:11:26.694715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19015","citing_title":"FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4PJLP4UV4S4TJI4MV7MMFVTM3I","json":"https://pith.science/pith/4PJLP4UV4S4TJI4MV7MMFVTM3I.json","graph_json":"https://pith.science/api/pith-number/4PJLP4UV4S4TJI4MV7MMFVTM3I/graph.json","events_json":"https://pith.science/api/pith-number/4PJLP4UV4S4TJI4MV7MMFVTM3I/events.json","paper":"https://pith.science/paper/4PJLP4UV"},"agent_actions":{"view_html":"https://pith.science/pith/4PJLP4UV4S4TJI4MV7MMFVTM3I","download_json":"https://pith.science/pith/4PJLP4UV4S4TJI4MV7MMFVTM3I.json","view_paper":"https://pith.science/paper/4PJLP4UV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15865&json=true","fetch_graph":"https://pith.science/api/pith-number/4PJLP4UV4S4TJI4MV7MMFVTM3I/graph.json","fetch_events":"https://pith.science/api/pith-number/4PJLP4UV4S4TJI4MV7MMFVTM3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PJLP4UV4S4TJI4MV7MMFVTM3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PJLP4UV4S4TJI4MV7MMFVTM3I/action/storage_attestation","attest_author":"https://pith.science/pith/4PJLP4UV4S4TJI4MV7MMFVTM3I/action/author_attestation","sign_citation":"https://pith.science/pith/4PJLP4UV4S4TJI4MV7MMFVTM3I/action/citation_signature","submit_replication":"https://pith.science/pith/4PJLP4UV4S4TJI4MV7MMFVTM3I/action/replication_record"}},"created_at":"2026-07-05T05:11:26.694715+00:00","updated_at":"2026-07-05T05:11:26.694715+00:00"}