{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FFPB4FBWGADG2LVB7WFJ3FLNLD","short_pith_number":"pith:FFPB4FBW","schema_version":"1.0","canonical_sha256":"295e1e143630066d2ea1fd8a9d956d58dee1edfa7a4d77bbbe3785d672d74dc8","source":{"kind":"arxiv","id":"2412.18355","version":2},"attestation_state":"computed","paper":{"title":"Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hanlin Gu, Hao Yu, Le Zhang, Lixin Fan, Qiang Yang, Tianrui Li, Xin Yang","submitted_at":"2024-12-24T11:35:40Z","abstract_excerpt":"Federated continual learning (FCL) allows each client to continually update its knowledge from task streams, enhancing the applicability of federated learning in real-world scenarios. However, FCL needs to address not only spatial data heterogeneity between clients but also temporal data heterogeneity between tasks. In this paper, empirical experiments demonstrate that such input-level heterogeneity significantly affects the model's internal parameters and outputs, leading to severe spatial-temporal catastrophic forgetting of local and previous knowledge. To this end, we propose Federated Tail"},"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":"2412.18355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T11:35:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f6eae384bdc2662579365bbc1a30c1955ad8062bbc7d8c110d8bdffa6dae237f","abstract_canon_sha256":"ae4684788e258096cd3c4e2d923c4c6146cb05d7788ee6003f54f925f9d53553"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:29.274162Z","signature_b64":"4sJPtm+u8Vvhtp2Kfo9rFJtB6Y5hjJByd5WCL0mevXVoP/vAK6Da3sPEExEhUXtqUMc+t1vd4Xvc2b54Esw0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"295e1e143630066d2ea1fd8a9d956d58dee1edfa7a4d77bbbe3785d672d74dc8","last_reissued_at":"2026-07-05T10:24:29.273675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:29.273675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hanlin Gu, Hao Yu, Le Zhang, Lixin Fan, Qiang Yang, Tianrui Li, Xin Yang","submitted_at":"2024-12-24T11:35:40Z","abstract_excerpt":"Federated continual learning (FCL) allows each client to continually update its knowledge from task streams, enhancing the applicability of federated learning in real-world scenarios. However, FCL needs to address not only spatial data heterogeneity between clients but also temporal data heterogeneity between tasks. In this paper, empirical experiments demonstrate that such input-level heterogeneity significantly affects the model's internal parameters and outputs, leading to severe spatial-temporal catastrophic forgetting of local and previous knowledge. To this end, we propose Federated Tail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18355","kind":"arxiv","version":2},"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/2412.18355/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":"2412.18355","created_at":"2026-07-05T10:24:29.273732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18355v2","created_at":"2026-07-05T10:24:29.273732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18355","created_at":"2026-07-05T10:24:29.273732+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFPB4FBWGADG","created_at":"2026-07-05T10:24:29.273732+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFPB4FBWGADG2LVB","created_at":"2026-07-05T10:24:29.273732+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFPB4FBW","created_at":"2026-07-05T10:24:29.273732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.18187","citing_title":"BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFPB4FBWGADG2LVB7WFJ3FLNLD","json":"https://pith.science/pith/FFPB4FBWGADG2LVB7WFJ3FLNLD.json","graph_json":"https://pith.science/api/pith-number/FFPB4FBWGADG2LVB7WFJ3FLNLD/graph.json","events_json":"https://pith.science/api/pith-number/FFPB4FBWGADG2LVB7WFJ3FLNLD/events.json","paper":"https://pith.science/paper/FFPB4FBW"},"agent_actions":{"view_html":"https://pith.science/pith/FFPB4FBWGADG2LVB7WFJ3FLNLD","download_json":"https://pith.science/pith/FFPB4FBWGADG2LVB7WFJ3FLNLD.json","view_paper":"https://pith.science/paper/FFPB4FBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18355&json=true","fetch_graph":"https://pith.science/api/pith-number/FFPB4FBWGADG2LVB7WFJ3FLNLD/graph.json","fetch_events":"https://pith.science/api/pith-number/FFPB4FBWGADG2LVB7WFJ3FLNLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFPB4FBWGADG2LVB7WFJ3FLNLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFPB4FBWGADG2LVB7WFJ3FLNLD/action/storage_attestation","attest_author":"https://pith.science/pith/FFPB4FBWGADG2LVB7WFJ3FLNLD/action/author_attestation","sign_citation":"https://pith.science/pith/FFPB4FBWGADG2LVB7WFJ3FLNLD/action/citation_signature","submit_replication":"https://pith.science/pith/FFPB4FBWGADG2LVB7WFJ3FLNLD/action/replication_record"}},"created_at":"2026-07-05T10:24:29.273732+00:00","updated_at":"2026-07-05T10:24:29.273732+00:00"}