{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5G7VFQV6WHYGD3OABORZ6EVM3P","short_pith_number":"pith:5G7VFQV6","schema_version":"1.0","canonical_sha256":"e9bf52c2beb1f061edc00ba39f12acdbc53f50a58992d831d7ae0fa9a8349d7c","source":{"kind":"arxiv","id":"2405.10647","version":1},"attestation_state":"computed","paper":{"title":"Cyclical Weight Consolidation: Towards Solving Catastrophic Forgetting in Serial Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Haoyue Song, Jiacheng Wang, Liansheng Wang","submitted_at":"2024-05-17T09:20:21Z","abstract_excerpt":"Federated Learning (FL) has gained attention for addressing data scarcity and privacy concerns. While parallel FL algorithms like FedAvg exhibit remarkable performance, they face challenges in scenarios with diverse network speeds and concerns about centralized control, especially in multi-institutional collaborations like the medical domain. Serial FL presents an alternative solution, circumventing these challenges by transferring model updates serially between devices in a cyclical manner. Nevertheless, it is deemed inferior to parallel FL in that (1) its performance shows undesirable fluctu"},"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":"2405.10647","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-17T09:20:21Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"b8998d447b8bb61120da15dcd318c8b4f55ebfba4d1ea07b3c62e4ec4c72c171","abstract_canon_sha256":"90fd584b3e90c84d52781354ac4ab2c7bec1e51e859b802819b260f45d43ef72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:14.859700Z","signature_b64":"kC/bcjww4buPcnfU9zzzJwm4BNL7lO0MohI3brWEjWXQNv/dV8DJxFOFtqBM4QhUyVNu8gcRfqNYwuPLssm7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9bf52c2beb1f061edc00ba39f12acdbc53f50a58992d831d7ae0fa9a8349d7c","last_reissued_at":"2026-07-05T08:20:14.859274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:14.859274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cyclical Weight Consolidation: Towards Solving Catastrophic Forgetting in Serial Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Haoyue Song, Jiacheng Wang, Liansheng Wang","submitted_at":"2024-05-17T09:20:21Z","abstract_excerpt":"Federated Learning (FL) has gained attention for addressing data scarcity and privacy concerns. While parallel FL algorithms like FedAvg exhibit remarkable performance, they face challenges in scenarios with diverse network speeds and concerns about centralized control, especially in multi-institutional collaborations like the medical domain. Serial FL presents an alternative solution, circumventing these challenges by transferring model updates serially between devices in a cyclical manner. Nevertheless, it is deemed inferior to parallel FL in that (1) its performance shows undesirable fluctu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10647","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/2405.10647/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":"2405.10647","created_at":"2026-07-05T08:20:14.859337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10647v1","created_at":"2026-07-05T08:20:14.859337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10647","created_at":"2026-07-05T08:20:14.859337+00:00"},{"alias_kind":"pith_short_12","alias_value":"5G7VFQV6WHYG","created_at":"2026-07-05T08:20:14.859337+00:00"},{"alias_kind":"pith_short_16","alias_value":"5G7VFQV6WHYGD3OA","created_at":"2026-07-05T08:20:14.859337+00:00"},{"alias_kind":"pith_short_8","alias_value":"5G7VFQV6","created_at":"2026-07-05T08:20:14.859337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08508","citing_title":"SFedKD: Sequential Federated Learning with Discrepancy-Aware Multi-Teacher Knowledge Distillation","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5G7VFQV6WHYGD3OABORZ6EVM3P","json":"https://pith.science/pith/5G7VFQV6WHYGD3OABORZ6EVM3P.json","graph_json":"https://pith.science/api/pith-number/5G7VFQV6WHYGD3OABORZ6EVM3P/graph.json","events_json":"https://pith.science/api/pith-number/5G7VFQV6WHYGD3OABORZ6EVM3P/events.json","paper":"https://pith.science/paper/5G7VFQV6"},"agent_actions":{"view_html":"https://pith.science/pith/5G7VFQV6WHYGD3OABORZ6EVM3P","download_json":"https://pith.science/pith/5G7VFQV6WHYGD3OABORZ6EVM3P.json","view_paper":"https://pith.science/paper/5G7VFQV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10647&json=true","fetch_graph":"https://pith.science/api/pith-number/5G7VFQV6WHYGD3OABORZ6EVM3P/graph.json","fetch_events":"https://pith.science/api/pith-number/5G7VFQV6WHYGD3OABORZ6EVM3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5G7VFQV6WHYGD3OABORZ6EVM3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5G7VFQV6WHYGD3OABORZ6EVM3P/action/storage_attestation","attest_author":"https://pith.science/pith/5G7VFQV6WHYGD3OABORZ6EVM3P/action/author_attestation","sign_citation":"https://pith.science/pith/5G7VFQV6WHYGD3OABORZ6EVM3P/action/citation_signature","submit_replication":"https://pith.science/pith/5G7VFQV6WHYGD3OABORZ6EVM3P/action/replication_record"}},"created_at":"2026-07-05T08:20:14.859337+00:00","updated_at":"2026-07-05T08:20:14.859337+00:00"}