{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z6USGZYNFHIR5LRMZC3IIM5ACK","short_pith_number":"pith:Z6USGZYN","schema_version":"1.0","canonical_sha256":"cfa923670d29d11eae2cc8b68433a0128d8b5c6ab1d0a17d8cbba98692898dfd","source":{"kind":"arxiv","id":"2309.01289","version":3},"attestation_state":"computed","paper":{"title":"Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Duygu Nur Yaldiz, Salman Avestimehr, Yahya H. Ezzeldin, Yavuz Faruk Bakman","submitted_at":"2023-09-03T23:21:17Z","abstract_excerpt":"Federated Learning (FL) has gained significant attraction due to its ability to enable privacy-preserving training over decentralized data. Current literature in FL mostly focuses on single-task learning. However, over time, new tasks may appear in the clients and the global model should learn these tasks without forgetting previous tasks. This real-world scenario is known as Continual Federated Learning (CFL). The main challenge of CFL is Global Catastrophic Forgetting, which corresponds to the fact that when the global model is trained on new tasks, its performance on old tasks decreases. Th"},"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":"2309.01289","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-03T23:21:17Z","cross_cats_sorted":[],"title_canon_sha256":"b66e51faf00563809b8ae313981ba135b5aac3d57edd0eb3db86a69eb365bcef","abstract_canon_sha256":"61953005cdf5f02936adfe4f969c1f7e8084c2233c6824a902b19a445d40b01b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:25.520767Z","signature_b64":"86MvrYXhGc4XFLk/saYdMJQIc/7aAH51GKol5YHSmcu7+FiWkoLLF+/NMdbOPNsYkkvgd84S5XeHgUnRNcUJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfa923670d29d11eae2cc8b68433a0128d8b5c6ab1d0a17d8cbba98692898dfd","last_reissued_at":"2026-07-05T07:01:25.520291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:25.520291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Duygu Nur Yaldiz, Salman Avestimehr, Yahya H. Ezzeldin, Yavuz Faruk Bakman","submitted_at":"2023-09-03T23:21:17Z","abstract_excerpt":"Federated Learning (FL) has gained significant attraction due to its ability to enable privacy-preserving training over decentralized data. Current literature in FL mostly focuses on single-task learning. However, over time, new tasks may appear in the clients and the global model should learn these tasks without forgetting previous tasks. This real-world scenario is known as Continual Federated Learning (CFL). The main challenge of CFL is Global Catastrophic Forgetting, which corresponds to the fact that when the global model is trained on new tasks, its performance on old tasks decreases. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01289","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/2309.01289/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":"2309.01289","created_at":"2026-07-05T07:01:25.520357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01289v3","created_at":"2026-07-05T07:01:25.520357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01289","created_at":"2026-07-05T07:01:25.520357+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6USGZYNFHIR","created_at":"2026-07-05T07:01:25.520357+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6USGZYNFHIR5LRM","created_at":"2026-07-05T07:01:25.520357+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6USGZYN","created_at":"2026-07-05T07:01:25.520357+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11480","citing_title":"Accurate and Resource-Efficient Federated Continual Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6USGZYNFHIR5LRMZC3IIM5ACK","json":"https://pith.science/pith/Z6USGZYNFHIR5LRMZC3IIM5ACK.json","graph_json":"https://pith.science/api/pith-number/Z6USGZYNFHIR5LRMZC3IIM5ACK/graph.json","events_json":"https://pith.science/api/pith-number/Z6USGZYNFHIR5LRMZC3IIM5ACK/events.json","paper":"https://pith.science/paper/Z6USGZYN"},"agent_actions":{"view_html":"https://pith.science/pith/Z6USGZYNFHIR5LRMZC3IIM5ACK","download_json":"https://pith.science/pith/Z6USGZYNFHIR5LRMZC3IIM5ACK.json","view_paper":"https://pith.science/paper/Z6USGZYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01289&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6USGZYNFHIR5LRMZC3IIM5ACK/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6USGZYNFHIR5LRMZC3IIM5ACK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6USGZYNFHIR5LRMZC3IIM5ACK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6USGZYNFHIR5LRMZC3IIM5ACK/action/storage_attestation","attest_author":"https://pith.science/pith/Z6USGZYNFHIR5LRMZC3IIM5ACK/action/author_attestation","sign_citation":"https://pith.science/pith/Z6USGZYNFHIR5LRMZC3IIM5ACK/action/citation_signature","submit_replication":"https://pith.science/pith/Z6USGZYNFHIR5LRMZC3IIM5ACK/action/replication_record"}},"created_at":"2026-07-05T07:01:25.520357+00:00","updated_at":"2026-07-05T07:01:25.520357+00:00"}