{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HZQQ7YHS2DPFPZT6MYCY7UEGFM","short_pith_number":"pith:HZQQ7YHS","schema_version":"1.0","canonical_sha256":"3e610fe0f2d0de57e67e66058fd0862b2b286eb6cf542e4dd71b566e3ee430b8","source":{"kind":"arxiv","id":"2507.04310","version":1},"attestation_state":"computed","paper":{"title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Daeyoung Choi, Gyuejeong Lee, Jihwan Shin","submitted_at":"2025-07-06T09:34:41Z","abstract_excerpt":"Heterogeneity in data distributions and model architectures remains a significant challenge in federated learning (FL). Various heterogeneous FL (HtFL) approaches have recently been proposed to address this challenge. Among them, prototype-based FL (PBFL) has emerged as a practical framework that only shares per-class mean activations from the penultimate layer. However, PBFL approaches often suffer from suboptimal prototype separation, limiting their discriminative power. We propose Prototype Normalization (ProtoNorm), a novel PBFL framework that addresses this limitation through two key comp"},"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":"2507.04310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-06T09:34:41Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"1d5bd09262468d20cb23716c9ed8f86357f999938ba14f89b926d574706dc64c","abstract_canon_sha256":"252968010fc83c0d7cd5943d80ed605c60f1e6c55d660ac3329a099dd9c61691"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:45.590991Z","signature_b64":"6iNGCn2TeGQdIVZcrcbn94cytZV3QQppmw67jRVE4EpWWcGHzOFut0jfrmBmzxwxfSZnNsxmTgZEQMJu6ad0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e610fe0f2d0de57e67e66058fd0862b2b286eb6cf542e4dd71b566e3ee430b8","last_reissued_at":"2026-07-05T11:32:45.590351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:45.590351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Daeyoung Choi, Gyuejeong Lee, Jihwan Shin","submitted_at":"2025-07-06T09:34:41Z","abstract_excerpt":"Heterogeneity in data distributions and model architectures remains a significant challenge in federated learning (FL). Various heterogeneous FL (HtFL) approaches have recently been proposed to address this challenge. Among them, prototype-based FL (PBFL) has emerged as a practical framework that only shares per-class mean activations from the penultimate layer. However, PBFL approaches often suffer from suboptimal prototype separation, limiting their discriminative power. We propose Prototype Normalization (ProtoNorm), a novel PBFL framework that addresses this limitation through two key comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04310","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/2507.04310/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":"2507.04310","created_at":"2026-07-05T11:32:45.590413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04310v1","created_at":"2026-07-05T11:32:45.590413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04310","created_at":"2026-07-05T11:32:45.590413+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZQQ7YHS2DPF","created_at":"2026-07-05T11:32:45.590413+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZQQ7YHS2DPFPZT6","created_at":"2026-07-05T11:32:45.590413+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZQQ7YHS","created_at":"2026-07-05T11:32:45.590413+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/HZQQ7YHS2DPFPZT6MYCY7UEGFM","json":"https://pith.science/pith/HZQQ7YHS2DPFPZT6MYCY7UEGFM.json","graph_json":"https://pith.science/api/pith-number/HZQQ7YHS2DPFPZT6MYCY7UEGFM/graph.json","events_json":"https://pith.science/api/pith-number/HZQQ7YHS2DPFPZT6MYCY7UEGFM/events.json","paper":"https://pith.science/paper/HZQQ7YHS"},"agent_actions":{"view_html":"https://pith.science/pith/HZQQ7YHS2DPFPZT6MYCY7UEGFM","download_json":"https://pith.science/pith/HZQQ7YHS2DPFPZT6MYCY7UEGFM.json","view_paper":"https://pith.science/paper/HZQQ7YHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04310&json=true","fetch_graph":"https://pith.science/api/pith-number/HZQQ7YHS2DPFPZT6MYCY7UEGFM/graph.json","fetch_events":"https://pith.science/api/pith-number/HZQQ7YHS2DPFPZT6MYCY7UEGFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZQQ7YHS2DPFPZT6MYCY7UEGFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZQQ7YHS2DPFPZT6MYCY7UEGFM/action/storage_attestation","attest_author":"https://pith.science/pith/HZQQ7YHS2DPFPZT6MYCY7UEGFM/action/author_attestation","sign_citation":"https://pith.science/pith/HZQQ7YHS2DPFPZT6MYCY7UEGFM/action/citation_signature","submit_replication":"https://pith.science/pith/HZQQ7YHS2DPFPZT6MYCY7UEGFM/action/replication_record"}},"created_at":"2026-07-05T11:32:45.590413+00:00","updated_at":"2026-07-05T11:32:45.590413+00:00"}