{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SK4CS7B2L3DRYN2EQKB75YTEHX","short_pith_number":"pith:SK4CS7B2","schema_version":"1.0","canonical_sha256":"92b8297c3a5ec71c37448283fee2643dd943a835659e39c7d2b26a0e863df400","source":{"kind":"arxiv","id":"2507.19822","version":1},"attestation_state":"computed","paper":{"title":"Debunking Optimization Myths in Federated Learning for Medical Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV","eess.SP"],"primary_cat":"cs.LG","authors_text":"Hyukjoon Lee, Jinu Gong, Joonhyuk Kang, Yang Cao, Youngjoon Lee","submitted_at":"2025-07-26T06:41:17Z","abstract_excerpt":"Federated Learning (FL) is a collaborative learning method that enables decentralized model training while preserving data privacy. Despite its promise in medical imaging, recent FL methods are often sensitive to local factors such as optimizers and learning rates, limiting their robustness in practical deployments. In this work, we revisit vanilla FL to clarify the impact of edge device configurations, benchmarking recent FL methods on colorectal pathology and blood cell classification task. We numerically show that the choice of local optimizer and learning rate has a greater effect on perfo"},"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":"2507.19822","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-26T06:41:17Z","cross_cats_sorted":["eess.IV","eess.SP"],"title_canon_sha256":"8018cebebd805a022f1cdd912e68c07050313fc00ab6c3c5334c8ab1c402ba10","abstract_canon_sha256":"a3550229e3fe64c67ab5b2013f399406a730d42f6e25de34f2e407f225913918"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:42.672429Z","signature_b64":"iNlkDjydKdlA/yVFhjp+w+4gVUA7jwPYuy2r9/EDXdWtZH40wcR+9WIdW33Uxj4gD+qY01nPL+ZZ3sH4v0cbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92b8297c3a5ec71c37448283fee2643dd943a835659e39c7d2b26a0e863df400","last_reissued_at":"2026-07-05T11:43:42.671996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:42.671996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Debunking Optimization Myths in Federated Learning for Medical Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV","eess.SP"],"primary_cat":"cs.LG","authors_text":"Hyukjoon Lee, Jinu Gong, Joonhyuk Kang, Yang Cao, Youngjoon Lee","submitted_at":"2025-07-26T06:41:17Z","abstract_excerpt":"Federated Learning (FL) is a collaborative learning method that enables decentralized model training while preserving data privacy. Despite its promise in medical imaging, recent FL methods are often sensitive to local factors such as optimizers and learning rates, limiting their robustness in practical deployments. In this work, we revisit vanilla FL to clarify the impact of edge device configurations, benchmarking recent FL methods on colorectal pathology and blood cell classification task. We numerically show that the choice of local optimizer and learning rate has a greater effect on perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19822","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/2507.19822/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":"2507.19822","created_at":"2026-07-05T11:43:42.672056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19822v1","created_at":"2026-07-05T11:43:42.672056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19822","created_at":"2026-07-05T11:43:42.672056+00:00"},{"alias_kind":"pith_short_12","alias_value":"SK4CS7B2L3DR","created_at":"2026-07-05T11:43:42.672056+00:00"},{"alias_kind":"pith_short_16","alias_value":"SK4CS7B2L3DRYN2E","created_at":"2026-07-05T11:43:42.672056+00:00"},{"alias_kind":"pith_short_8","alias_value":"SK4CS7B2","created_at":"2026-07-05T11:43:42.672056+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/SK4CS7B2L3DRYN2EQKB75YTEHX","json":"https://pith.science/pith/SK4CS7B2L3DRYN2EQKB75YTEHX.json","graph_json":"https://pith.science/api/pith-number/SK4CS7B2L3DRYN2EQKB75YTEHX/graph.json","events_json":"https://pith.science/api/pith-number/SK4CS7B2L3DRYN2EQKB75YTEHX/events.json","paper":"https://pith.science/paper/SK4CS7B2"},"agent_actions":{"view_html":"https://pith.science/pith/SK4CS7B2L3DRYN2EQKB75YTEHX","download_json":"https://pith.science/pith/SK4CS7B2L3DRYN2EQKB75YTEHX.json","view_paper":"https://pith.science/paper/SK4CS7B2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19822&json=true","fetch_graph":"https://pith.science/api/pith-number/SK4CS7B2L3DRYN2EQKB75YTEHX/graph.json","fetch_events":"https://pith.science/api/pith-number/SK4CS7B2L3DRYN2EQKB75YTEHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SK4CS7B2L3DRYN2EQKB75YTEHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SK4CS7B2L3DRYN2EQKB75YTEHX/action/storage_attestation","attest_author":"https://pith.science/pith/SK4CS7B2L3DRYN2EQKB75YTEHX/action/author_attestation","sign_citation":"https://pith.science/pith/SK4CS7B2L3DRYN2EQKB75YTEHX/action/citation_signature","submit_replication":"https://pith.science/pith/SK4CS7B2L3DRYN2EQKB75YTEHX/action/replication_record"}},"created_at":"2026-07-05T11:43:42.672056+00:00","updated_at":"2026-07-05T11:43:42.672056+00:00"}