{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5H6ZP4DSOQN3HEEY4TSY5XPD5U","short_pith_number":"pith:5H6ZP4DS","schema_version":"1.0","canonical_sha256":"e9fd97f072741bb39098e4e58edde3ed0c9ab0a73c42df00e529bb3ca279e908","source":{"kind":"arxiv","id":"2501.05496","version":2},"attestation_state":"computed","paper":{"title":"FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenlong You, Chunmao Cai, Jingyue Tang, Jiyang Zhou, Xiangmou Qu, Xin Zheng, Yanbing Zhou, Yingbo Wu","submitted_at":"2025-01-09T16:10:03Z","abstract_excerpt":"Prototype-based federated learning has emerged as a promising approach that shares lightweight prototypes to transfer knowledge among clients with data heterogeneity in a model-agnostic manner. However, existing methods often collect prototypes directly from local models, which inevitably introduce inconsistencies into representation learning due to the biased data distributions and differing model architectures among clients. In this paper, we identify that both statistical and model heterogeneity create a vicious cycle of representation inconsistency, classifier divergence, and skewed protot"},"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":"2501.05496","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-09T16:10:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7eb61afa1d6a9371f8bde2d5723fd0e931d949be333d405d12b8b5fa6fe216f9","abstract_canon_sha256":"939e59807c9b4f9e6ee2b78760a416f0efa155fe884a21db18a391a2aad44d80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:30.743919Z","signature_b64":"nMGzrrPXfFjcYF3pkVx6VJxYqBpshMtWrsIjBPMnF98hAqlUP7+QmhVnh0KxXXoIq5Jh+2rcE9b9fASAmYmDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9fd97f072741bb39098e4e58edde3ed0c9ab0a73c42df00e529bb3ca279e908","last_reissued_at":"2026-07-05T11:01:30.743455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:30.743455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenlong You, Chunmao Cai, Jingyue Tang, Jiyang Zhou, Xiangmou Qu, Xin Zheng, Yanbing Zhou, Yingbo Wu","submitted_at":"2025-01-09T16:10:03Z","abstract_excerpt":"Prototype-based federated learning has emerged as a promising approach that shares lightweight prototypes to transfer knowledge among clients with data heterogeneity in a model-agnostic manner. However, existing methods often collect prototypes directly from local models, which inevitably introduce inconsistencies into representation learning due to the biased data distributions and differing model architectures among clients. In this paper, we identify that both statistical and model heterogeneity create a vicious cycle of representation inconsistency, classifier divergence, and skewed protot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05496","kind":"arxiv","version":2},"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/2501.05496/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":"2501.05496","created_at":"2026-07-05T11:01:30.743507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05496v2","created_at":"2026-07-05T11:01:30.743507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05496","created_at":"2026-07-05T11:01:30.743507+00:00"},{"alias_kind":"pith_short_12","alias_value":"5H6ZP4DSOQN3","created_at":"2026-07-05T11:01:30.743507+00:00"},{"alias_kind":"pith_short_16","alias_value":"5H6ZP4DSOQN3HEEY","created_at":"2026-07-05T11:01:30.743507+00:00"},{"alias_kind":"pith_short_8","alias_value":"5H6ZP4DS","created_at":"2026-07-05T11:01:30.743507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.13543","citing_title":"Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05959","citing_title":"From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5H6ZP4DSOQN3HEEY4TSY5XPD5U","json":"https://pith.science/pith/5H6ZP4DSOQN3HEEY4TSY5XPD5U.json","graph_json":"https://pith.science/api/pith-number/5H6ZP4DSOQN3HEEY4TSY5XPD5U/graph.json","events_json":"https://pith.science/api/pith-number/5H6ZP4DSOQN3HEEY4TSY5XPD5U/events.json","paper":"https://pith.science/paper/5H6ZP4DS"},"agent_actions":{"view_html":"https://pith.science/pith/5H6ZP4DSOQN3HEEY4TSY5XPD5U","download_json":"https://pith.science/pith/5H6ZP4DSOQN3HEEY4TSY5XPD5U.json","view_paper":"https://pith.science/paper/5H6ZP4DS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05496&json=true","fetch_graph":"https://pith.science/api/pith-number/5H6ZP4DSOQN3HEEY4TSY5XPD5U/graph.json","fetch_events":"https://pith.science/api/pith-number/5H6ZP4DSOQN3HEEY4TSY5XPD5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5H6ZP4DSOQN3HEEY4TSY5XPD5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5H6ZP4DSOQN3HEEY4TSY5XPD5U/action/storage_attestation","attest_author":"https://pith.science/pith/5H6ZP4DSOQN3HEEY4TSY5XPD5U/action/author_attestation","sign_citation":"https://pith.science/pith/5H6ZP4DSOQN3HEEY4TSY5XPD5U/action/citation_signature","submit_replication":"https://pith.science/pith/5H6ZP4DSOQN3HEEY4TSY5XPD5U/action/replication_record"}},"created_at":"2026-07-05T11:01:30.743507+00:00","updated_at":"2026-07-05T11:01:30.743507+00:00"}