{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MPALZOOECK5QI2QKNE6E6PB4SD","short_pith_number":"pith:MPALZOOE","schema_version":"1.0","canonical_sha256":"63c0bcb9c412bb046a0a693c4f3c3c90d88f9e4240ea03cdb950a8be8c95ac57","source":{"kind":"arxiv","id":"2106.06042","version":3},"attestation_state":"computed","paper":{"title":"FedBABU: Towards Enhanced Representation for Federated Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaehoon Oh, Sangmook Kim, Se-Young Yun","submitted_at":"2021-06-04T04:34:26Z","abstract_excerpt":"Federated learning has evolved to improve a single global model under data heterogeneity (as a curse) or to develop multiple personalized models using data heterogeneity (as a blessing). However, little research has considered both directions simultaneously. In this paper, we first investigate the relationship between them by analyzing Federated Averaging at the client level and determine that a better federated global model performance does not constantly improve personalization. To elucidate the cause of this personalization performance degradation problem, we decompose the entire network in"},"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":"2106.06042","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-04T04:34:26Z","cross_cats_sorted":[],"title_canon_sha256":"e52a3805e51896328d93285c0d26a735a7d8b2dd0988b7bc88a2b3c8647d37bd","abstract_canon_sha256":"44e30c132f755954adf34b19839d8ea58270b72d46c2f186bdbb4c22de733a0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:31.634543Z","signature_b64":"k//EoVNG8B/3V3+XFwddFuvaw1hDJRmtUVkptddEsNdE2H1AIZRJzbuk71clTmI/KR3M3j/9R8E3z+hT9A7WAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63c0bcb9c412bb046a0a693c4f3c3c90d88f9e4240ea03cdb950a8be8c95ac57","last_reissued_at":"2026-07-05T04:05:31.634101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:31.634101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedBABU: Towards Enhanced Representation for Federated Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaehoon Oh, Sangmook Kim, Se-Young Yun","submitted_at":"2021-06-04T04:34:26Z","abstract_excerpt":"Federated learning has evolved to improve a single global model under data heterogeneity (as a curse) or to develop multiple personalized models using data heterogeneity (as a blessing). However, little research has considered both directions simultaneously. In this paper, we first investigate the relationship between them by analyzing Federated Averaging at the client level and determine that a better federated global model performance does not constantly improve personalization. To elucidate the cause of this personalization performance degradation problem, we decompose the entire network in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06042","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/2106.06042/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":"2106.06042","created_at":"2026-07-05T04:05:31.634168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06042v3","created_at":"2026-07-05T04:05:31.634168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06042","created_at":"2026-07-05T04:05:31.634168+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPALZOOECK5Q","created_at":"2026-07-05T04:05:31.634168+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPALZOOECK5QI2QK","created_at":"2026-07-05T04:05:31.634168+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPALZOOE","created_at":"2026-07-05T04:05:31.634168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27816","citing_title":"Pattern Recognition Tasks with Personalized Federated Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00578","citing_title":"Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02004","citing_title":"Personalized Digital Health Modeling with Adaptive Support Users","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12168","citing_title":"On What We Can Learn from Low-Resolution Data","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06446","citing_title":"FedFrozen: Two-Stage Federated Optimization via Attention Kernel Freezing","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00698","citing_title":"FedKPer: Tackling Generalization and Personalization in Medical Federated Learning via Knowledge Personalization","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02004","citing_title":"Personalized Digital Health Modeling with Adaptive Support Users","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MPALZOOECK5QI2QKNE6E6PB4SD","json":"https://pith.science/pith/MPALZOOECK5QI2QKNE6E6PB4SD.json","graph_json":"https://pith.science/api/pith-number/MPALZOOECK5QI2QKNE6E6PB4SD/graph.json","events_json":"https://pith.science/api/pith-number/MPALZOOECK5QI2QKNE6E6PB4SD/events.json","paper":"https://pith.science/paper/MPALZOOE"},"agent_actions":{"view_html":"https://pith.science/pith/MPALZOOECK5QI2QKNE6E6PB4SD","download_json":"https://pith.science/pith/MPALZOOECK5QI2QKNE6E6PB4SD.json","view_paper":"https://pith.science/paper/MPALZOOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06042&json=true","fetch_graph":"https://pith.science/api/pith-number/MPALZOOECK5QI2QKNE6E6PB4SD/graph.json","fetch_events":"https://pith.science/api/pith-number/MPALZOOECK5QI2QKNE6E6PB4SD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPALZOOECK5QI2QKNE6E6PB4SD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPALZOOECK5QI2QKNE6E6PB4SD/action/storage_attestation","attest_author":"https://pith.science/pith/MPALZOOECK5QI2QKNE6E6PB4SD/action/author_attestation","sign_citation":"https://pith.science/pith/MPALZOOECK5QI2QKNE6E6PB4SD/action/citation_signature","submit_replication":"https://pith.science/pith/MPALZOOECK5QI2QKNE6E6PB4SD/action/replication_record"}},"created_at":"2026-07-05T04:05:31.634168+00:00","updated_at":"2026-07-05T04:05:31.634168+00:00"}