{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JOZT2HXBTBN5IU63ZPEG3FILHA","short_pith_number":"pith:JOZT2HXB","schema_version":"1.0","canonical_sha256":"4bb33d1ee1985bd453dbcbc86d950b383a84c3c3aacd73a18a2d3a0d89b2d49e","source":{"kind":"arxiv","id":"2310.15054","version":1},"attestation_state":"computed","paper":{"title":"Coordinated Replay Sample Selection for Continual Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charith Peris, Christophe Dupuy, Clement Chung, Jack Good, Jimit Majmudar, Jixuan Wang, Rahul Gupta, Richard Zemel","submitted_at":"2023-10-23T15:56:39Z","abstract_excerpt":"Continual Federated Learning (CFL) combines Federated Learning (FL), the decentralized learning of a central model on a number of client devices that may not communicate their data, and Continual Learning (CL), the learning of a model from a continual stream of data without keeping the entire history. In CL, the main challenge is \\textit{forgetting} what was learned from past data. While replay-based algorithms that keep a small pool of past training data are effective to reduce forgetting, only simple replay sample selection strategies have been applied to CFL in prior work, and no previous w"},"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":"2310.15054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T15:56:39Z","cross_cats_sorted":[],"title_canon_sha256":"9e20c75db5b261c37aa78c07b9019ecd8ecdf14ad01756332bc70c716a780f57","abstract_canon_sha256":"5401ed48ce87f200b73fb768c9c8721bcbb14b178b13672c7d0efb76e3af9308"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:05.322080Z","signature_b64":"y+gpb6foqf74hFoa3XVpvWAeA2GNo6Nh7kNXSDZTEcEmO0SRNvbl4/z19DdvynXjDIb442jpYbLCbPPsfRJuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bb33d1ee1985bd453dbcbc86d950b383a84c3c3aacd73a18a2d3a0d89b2d49e","last_reissued_at":"2026-07-05T07:04:05.321548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:05.321548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coordinated Replay Sample Selection for Continual Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charith Peris, Christophe Dupuy, Clement Chung, Jack Good, Jimit Majmudar, Jixuan Wang, Rahul Gupta, Richard Zemel","submitted_at":"2023-10-23T15:56:39Z","abstract_excerpt":"Continual Federated Learning (CFL) combines Federated Learning (FL), the decentralized learning of a central model on a number of client devices that may not communicate their data, and Continual Learning (CL), the learning of a model from a continual stream of data without keeping the entire history. In CL, the main challenge is \\textit{forgetting} what was learned from past data. While replay-based algorithms that keep a small pool of past training data are effective to reduce forgetting, only simple replay sample selection strategies have been applied to CFL in prior work, and no previous w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15054","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/2310.15054/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":"2310.15054","created_at":"2026-07-05T07:04:05.321610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15054v1","created_at":"2026-07-05T07:04:05.321610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15054","created_at":"2026-07-05T07:04:05.321610+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOZT2HXBTBN5","created_at":"2026-07-05T07:04:05.321610+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOZT2HXBTBN5IU63","created_at":"2026-07-05T07:04:05.321610+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOZT2HXB","created_at":"2026-07-05T07:04:05.321610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07059","citing_title":"Federated Continual Learning: Concepts, Challenges, and Solutions","ref_index":99,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOZT2HXBTBN5IU63ZPEG3FILHA","json":"https://pith.science/pith/JOZT2HXBTBN5IU63ZPEG3FILHA.json","graph_json":"https://pith.science/api/pith-number/JOZT2HXBTBN5IU63ZPEG3FILHA/graph.json","events_json":"https://pith.science/api/pith-number/JOZT2HXBTBN5IU63ZPEG3FILHA/events.json","paper":"https://pith.science/paper/JOZT2HXB"},"agent_actions":{"view_html":"https://pith.science/pith/JOZT2HXBTBN5IU63ZPEG3FILHA","download_json":"https://pith.science/pith/JOZT2HXBTBN5IU63ZPEG3FILHA.json","view_paper":"https://pith.science/paper/JOZT2HXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15054&json=true","fetch_graph":"https://pith.science/api/pith-number/JOZT2HXBTBN5IU63ZPEG3FILHA/graph.json","fetch_events":"https://pith.science/api/pith-number/JOZT2HXBTBN5IU63ZPEG3FILHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOZT2HXBTBN5IU63ZPEG3FILHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOZT2HXBTBN5IU63ZPEG3FILHA/action/storage_attestation","attest_author":"https://pith.science/pith/JOZT2HXBTBN5IU63ZPEG3FILHA/action/author_attestation","sign_citation":"https://pith.science/pith/JOZT2HXBTBN5IU63ZPEG3FILHA/action/citation_signature","submit_replication":"https://pith.science/pith/JOZT2HXBTBN5IU63ZPEG3FILHA/action/replication_record"}},"created_at":"2026-07-05T07:04:05.321610+00:00","updated_at":"2026-07-05T07:04:05.321610+00:00"}