{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O2LLY7S6UDDQZ2MZ4PN44O6TJD","short_pith_number":"pith:O2LLY7S6","schema_version":"1.0","canonical_sha256":"7696bc7e5ea0c70ce999e3dbce3bd348c912422558f09786fca172812d4a0c5c","source":{"kind":"arxiv","id":"2503.18064","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for FCL","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Guanyu Yang, Huazhu Fu, Jingyang Zhang, Shuo Li, Xiaoming Qi, Yueming Jin","submitted_at":"2025-03-23T13:12:56Z","abstract_excerpt":"Federated continual learning (FCL) offers an emerging pattern to facilitate the applicability of federated learning (FL) in real-world scenarios, where tasks evolve dynamically and asynchronously across clients, especially in medical scenario. Existing server-side FCL methods in nature domain construct a continually learnable server model by client aggregation on all-involved tasks. However, they are challenged by: (1) Catastrophic forgetting for previously learned tasks, leading to error accumulation in server model, making it difficult to sustain comprehensive knowledge across all tasks. (2)"},"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":"2503.18064","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-23T13:12:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"503e18cc5187d43d1b3129ba5e5457e5f9f0349c73a5d5f3617ebf9213a14113","abstract_canon_sha256":"b948dbf17b90e0aa54f4836911915e98cf58ce1025362977f31ec480d91ee665"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:01.797546Z","signature_b64":"2HisWhkFJPXo03ZNjOdvOf+LJ8mAbL8R+0aMvEBvwMzC9ffHEhZ5n16vNlNi/Cg/ykr4rh4usUB3QtQ2lJ+3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7696bc7e5ea0c70ce999e3dbce3bd348c912422558f09786fca172812d4a0c5c","last_reissued_at":"2026-07-05T10:38:01.796941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:01.796941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for FCL","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Guanyu Yang, Huazhu Fu, Jingyang Zhang, Shuo Li, Xiaoming Qi, Yueming Jin","submitted_at":"2025-03-23T13:12:56Z","abstract_excerpt":"Federated continual learning (FCL) offers an emerging pattern to facilitate the applicability of federated learning (FL) in real-world scenarios, where tasks evolve dynamically and asynchronously across clients, especially in medical scenario. Existing server-side FCL methods in nature domain construct a continually learnable server model by client aggregation on all-involved tasks. However, they are challenged by: (1) Catastrophic forgetting for previously learned tasks, leading to error accumulation in server model, making it difficult to sustain comprehensive knowledge across all tasks. (2)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18064","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/2503.18064/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":"2503.18064","created_at":"2026-07-05T10:38:01.797022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18064v1","created_at":"2026-07-05T10:38:01.797022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18064","created_at":"2026-07-05T10:38:01.797022+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2LLY7S6UDDQ","created_at":"2026-07-05T10:38:01.797022+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2LLY7S6UDDQZ2MZ","created_at":"2026-07-05T10:38:01.797022+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2LLY7S6","created_at":"2026-07-05T10:38:01.797022+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/O2LLY7S6UDDQZ2MZ4PN44O6TJD","json":"https://pith.science/pith/O2LLY7S6UDDQZ2MZ4PN44O6TJD.json","graph_json":"https://pith.science/api/pith-number/O2LLY7S6UDDQZ2MZ4PN44O6TJD/graph.json","events_json":"https://pith.science/api/pith-number/O2LLY7S6UDDQZ2MZ4PN44O6TJD/events.json","paper":"https://pith.science/paper/O2LLY7S6"},"agent_actions":{"view_html":"https://pith.science/pith/O2LLY7S6UDDQZ2MZ4PN44O6TJD","download_json":"https://pith.science/pith/O2LLY7S6UDDQZ2MZ4PN44O6TJD.json","view_paper":"https://pith.science/paper/O2LLY7S6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18064&json=true","fetch_graph":"https://pith.science/api/pith-number/O2LLY7S6UDDQZ2MZ4PN44O6TJD/graph.json","fetch_events":"https://pith.science/api/pith-number/O2LLY7S6UDDQZ2MZ4PN44O6TJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2LLY7S6UDDQZ2MZ4PN44O6TJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2LLY7S6UDDQZ2MZ4PN44O6TJD/action/storage_attestation","attest_author":"https://pith.science/pith/O2LLY7S6UDDQZ2MZ4PN44O6TJD/action/author_attestation","sign_citation":"https://pith.science/pith/O2LLY7S6UDDQZ2MZ4PN44O6TJD/action/citation_signature","submit_replication":"https://pith.science/pith/O2LLY7S6UDDQZ2MZ4PN44O6TJD/action/replication_record"}},"created_at":"2026-07-05T10:38:01.797022+00:00","updated_at":"2026-07-05T10:38:01.797022+00:00"}