{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H4HIN3KQGG6H3YNKFHM2AGLFCY","short_pith_number":"pith:H4HIN3KQ","schema_version":"1.0","canonical_sha256":"3f0e86ed5031bc7de1aa29d9a019651616a212bc1b1e384aa24d1b3067fe5f8c","source":{"kind":"arxiv","id":"2411.09842","version":1},"attestation_state":"computed","paper":{"title":"FedRewind: Rewinding Continual Model Exchange for Decentralized Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Concetto Spampinato, Federica Proietto Salanitri, Giovanni Bellitto, Luca Palazzo, Matteo Pennisi, Simone Palazzo","submitted_at":"2024-11-14T23:14:43Z","abstract_excerpt":"In this paper, we present FedRewind, a novel approach to decentralized federated learning that leverages model exchange among nodes to address the issue of data distribution shift. Drawing inspiration from continual learning (CL) principles and cognitive neuroscience theories for memory retention, FedRewind implements a decentralized routing mechanism where nodes send/receive models to/from other nodes in the federation to address spatial distribution challenges inherent in distributed learning (FL). During local training, federation nodes periodically send their models back (i.e., rewind) to "},"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":"2411.09842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T23:14:43Z","cross_cats_sorted":[],"title_canon_sha256":"d938529a910a6e3900e1aaf7cf4db673f0a264991d2102a28641093a1a210911","abstract_canon_sha256":"fa021230e1c3c8cb3e57cefbbc9195f409bbb7699af2476f66fd86ea06c5e6ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:39.156842Z","signature_b64":"ghNw28yjvlhezrpcGLcVEokpb3G40H/NmtJKuBybkhBeo7p3VxGDWtsSDySggdmX4+hl9WyUXxpYLmsFbbvyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f0e86ed5031bc7de1aa29d9a019651616a212bc1b1e384aa24d1b3067fe5f8c","last_reissued_at":"2026-07-05T09:35:39.156432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:39.156432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedRewind: Rewinding Continual Model Exchange for Decentralized Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Concetto Spampinato, Federica Proietto Salanitri, Giovanni Bellitto, Luca Palazzo, Matteo Pennisi, Simone Palazzo","submitted_at":"2024-11-14T23:14:43Z","abstract_excerpt":"In this paper, we present FedRewind, a novel approach to decentralized federated learning that leverages model exchange among nodes to address the issue of data distribution shift. Drawing inspiration from continual learning (CL) principles and cognitive neuroscience theories for memory retention, FedRewind implements a decentralized routing mechanism where nodes send/receive models to/from other nodes in the federation to address spatial distribution challenges inherent in distributed learning (FL). During local training, federation nodes periodically send their models back (i.e., rewind) to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09842","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/2411.09842/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":"2411.09842","created_at":"2026-07-05T09:35:39.156496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09842v1","created_at":"2026-07-05T09:35:39.156496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09842","created_at":"2026-07-05T09:35:39.156496+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4HIN3KQGG6H","created_at":"2026-07-05T09:35:39.156496+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4HIN3KQGG6H3YNK","created_at":"2026-07-05T09:35:39.156496+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4HIN3KQ","created_at":"2026-07-05T09:35:39.156496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03320","citing_title":"The Future of Continual Learning in the Era of Foundation Models: Three Key Directions","ref_index":100,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4HIN3KQGG6H3YNKFHM2AGLFCY","json":"https://pith.science/pith/H4HIN3KQGG6H3YNKFHM2AGLFCY.json","graph_json":"https://pith.science/api/pith-number/H4HIN3KQGG6H3YNKFHM2AGLFCY/graph.json","events_json":"https://pith.science/api/pith-number/H4HIN3KQGG6H3YNKFHM2AGLFCY/events.json","paper":"https://pith.science/paper/H4HIN3KQ"},"agent_actions":{"view_html":"https://pith.science/pith/H4HIN3KQGG6H3YNKFHM2AGLFCY","download_json":"https://pith.science/pith/H4HIN3KQGG6H3YNKFHM2AGLFCY.json","view_paper":"https://pith.science/paper/H4HIN3KQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09842&json=true","fetch_graph":"https://pith.science/api/pith-number/H4HIN3KQGG6H3YNKFHM2AGLFCY/graph.json","fetch_events":"https://pith.science/api/pith-number/H4HIN3KQGG6H3YNKFHM2AGLFCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4HIN3KQGG6H3YNKFHM2AGLFCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4HIN3KQGG6H3YNKFHM2AGLFCY/action/storage_attestation","attest_author":"https://pith.science/pith/H4HIN3KQGG6H3YNKFHM2AGLFCY/action/author_attestation","sign_citation":"https://pith.science/pith/H4HIN3KQGG6H3YNKFHM2AGLFCY/action/citation_signature","submit_replication":"https://pith.science/pith/H4HIN3KQGG6H3YNKFHM2AGLFCY/action/replication_record"}},"created_at":"2026-07-05T09:35:39.156496+00:00","updated_at":"2026-07-05T09:35:39.156496+00:00"}