{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FJWS5BIJKUUMQ2DHKQFHM5N7EO","short_pith_number":"pith:FJWS5BIJ","schema_version":"1.0","canonical_sha256":"2a6d2e85095528c86867540a7675bf23892cc1a70eacbdf855d31078c6690d84","source":{"kind":"arxiv","id":"2508.21286","version":1},"attestation_state":"computed","paper":{"title":"Decentralized Federated Averaging via Random Walk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Changheng Wang, Lizhe Liu, Qiao Deng, Yangyang Niu, Yashan Pang, Yingda Wu, Zhiqing Wei, Zhiyong Feng","submitted_at":"2025-08-29T01:13:41Z","abstract_excerpt":"Federated Learning (FL) is a communication-efficient distributed machine learning method that allows multiple devices to collaboratively train models without sharing raw data. FL can be categorized into centralized and decentralized paradigms. The centralized paradigm relies on a central server to aggregate local models, potentially resulting in single points of failure, communication bottlenecks, and exposure of model parameters. In contrast, the decentralized paradigm, which does not require a central server, provides improved robustness and privacy. The essence of federated learning lies in"},"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":"2508.21286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-08-29T01:13:41Z","cross_cats_sorted":[],"title_canon_sha256":"11e18aff96c9a641e53ad4e7b0aebd9270c643cbf713d106c05e5b0ad82d0421","abstract_canon_sha256":"9fc86d8f5ff78d9be1623a1c0b8c653704dce3e320008f03d2dc53a351fbd165"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:31.879770Z","signature_b64":"fyqrk1efDAKVURYiXcMM7nRPAdRNC6BsTgKZhNg9YHZsuuKA75F82u8uz7o+6pB1FCIAI3gjb2is90q5yqB9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a6d2e85095528c86867540a7675bf23892cc1a70eacbdf855d31078c6690d84","last_reissued_at":"2026-07-05T12:01:31.879361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:31.879361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Federated Averaging via Random Walk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Changheng Wang, Lizhe Liu, Qiao Deng, Yangyang Niu, Yashan Pang, Yingda Wu, Zhiqing Wei, Zhiyong Feng","submitted_at":"2025-08-29T01:13:41Z","abstract_excerpt":"Federated Learning (FL) is a communication-efficient distributed machine learning method that allows multiple devices to collaboratively train models without sharing raw data. FL can be categorized into centralized and decentralized paradigms. The centralized paradigm relies on a central server to aggregate local models, potentially resulting in single points of failure, communication bottlenecks, and exposure of model parameters. In contrast, the decentralized paradigm, which does not require a central server, provides improved robustness and privacy. The essence of federated learning lies in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21286","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/2508.21286/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":"2508.21286","created_at":"2026-07-05T12:01:31.879419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21286v1","created_at":"2026-07-05T12:01:31.879419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21286","created_at":"2026-07-05T12:01:31.879419+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJWS5BIJKUUM","created_at":"2026-07-05T12:01:31.879419+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJWS5BIJKUUMQ2DH","created_at":"2026-07-05T12:01:31.879419+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJWS5BIJ","created_at":"2026-07-05T12:01:31.879419+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/FJWS5BIJKUUMQ2DHKQFHM5N7EO","json":"https://pith.science/pith/FJWS5BIJKUUMQ2DHKQFHM5N7EO.json","graph_json":"https://pith.science/api/pith-number/FJWS5BIJKUUMQ2DHKQFHM5N7EO/graph.json","events_json":"https://pith.science/api/pith-number/FJWS5BIJKUUMQ2DHKQFHM5N7EO/events.json","paper":"https://pith.science/paper/FJWS5BIJ"},"agent_actions":{"view_html":"https://pith.science/pith/FJWS5BIJKUUMQ2DHKQFHM5N7EO","download_json":"https://pith.science/pith/FJWS5BIJKUUMQ2DHKQFHM5N7EO.json","view_paper":"https://pith.science/paper/FJWS5BIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21286&json=true","fetch_graph":"https://pith.science/api/pith-number/FJWS5BIJKUUMQ2DHKQFHM5N7EO/graph.json","fetch_events":"https://pith.science/api/pith-number/FJWS5BIJKUUMQ2DHKQFHM5N7EO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJWS5BIJKUUMQ2DHKQFHM5N7EO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJWS5BIJKUUMQ2DHKQFHM5N7EO/action/storage_attestation","attest_author":"https://pith.science/pith/FJWS5BIJKUUMQ2DHKQFHM5N7EO/action/author_attestation","sign_citation":"https://pith.science/pith/FJWS5BIJKUUMQ2DHKQFHM5N7EO/action/citation_signature","submit_replication":"https://pith.science/pith/FJWS5BIJKUUMQ2DHKQFHM5N7EO/action/replication_record"}},"created_at":"2026-07-05T12:01:31.879419+00:00","updated_at":"2026-07-05T12:01:31.879419+00:00"}