{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PV3XCI2BXUYEXDCBYY55UINWZD","short_pith_number":"pith:PV3XCI2B","schema_version":"1.0","canonical_sha256":"7d77712341bd304b8c41c63bda21b6c8f34d54d63c91eaa95f5b501ecce3d7dc","source":{"kind":"arxiv","id":"2407.11762","version":2},"attestation_state":"computed","paper":{"title":"Self-Regulating Random Walks for Resilient Decentralized Learning on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IT","math.IT","stat.AP"],"primary_cat":"cs.LG","authors_text":"Antonia Wachter-Zeh, Ghadir Ayache, Maximilian Egger, Rawad Bitar, Salim El Rouayheb","submitted_at":"2024-07-16T14:22:22Z","abstract_excerpt":"Consider the setting of multiple random walks (RWs) on a graph executing a certain computational task. For instance, in decentralized learning via RWs, a model is updated at each iteration based on the local data of the visited node and then passed to a randomly chosen neighbor. RWs can fail due to node or link failures. The goal is to maintain a desired number of RWs to ensure failure resilience. Achieving this is challenging due to the lack of a central entity to track which RWs have failed to replace them with new ones by forking (duplicating) surviving ones. Without duplications, the numbe"},"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":"2407.11762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T14:22:22Z","cross_cats_sorted":["cs.DC","cs.IT","math.IT","stat.AP"],"title_canon_sha256":"9e97cd70eb58e388b6f201dd163ee22959b22509acdd154575b741665dddb4e4","abstract_canon_sha256":"d7e986fcab4af74f00bfc14b661c42b26bfd71576b2aa3d454e65553b98cf9c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:59.643214Z","signature_b64":"wu76pJu/tfHZq0BxCKOQ3ZmHcUKLNy1HkaWyPRT8AGlx7zPbrCYSGUszkNppDIYpT4gkupE03gwNEolh3t/qBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d77712341bd304b8c41c63bda21b6c8f34d54d63c91eaa95f5b501ecce3d7dc","last_reissued_at":"2026-07-05T10:11:59.642549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:59.642549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Regulating Random Walks for Resilient Decentralized Learning on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.IT","math.IT","stat.AP"],"primary_cat":"cs.LG","authors_text":"Antonia Wachter-Zeh, Ghadir Ayache, Maximilian Egger, Rawad Bitar, Salim El Rouayheb","submitted_at":"2024-07-16T14:22:22Z","abstract_excerpt":"Consider the setting of multiple random walks (RWs) on a graph executing a certain computational task. For instance, in decentralized learning via RWs, a model is updated at each iteration based on the local data of the visited node and then passed to a randomly chosen neighbor. RWs can fail due to node or link failures. The goal is to maintain a desired number of RWs to ensure failure resilience. Achieving this is challenging due to the lack of a central entity to track which RWs have failed to replace them with new ones by forking (duplicating) surviving ones. Without duplications, the numbe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11762","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/2407.11762/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":"2407.11762","created_at":"2026-07-05T10:11:59.642618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11762v2","created_at":"2026-07-05T10:11:59.642618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11762","created_at":"2026-07-05T10:11:59.642618+00:00"},{"alias_kind":"pith_short_12","alias_value":"PV3XCI2BXUYE","created_at":"2026-07-05T10:11:59.642618+00:00"},{"alias_kind":"pith_short_16","alias_value":"PV3XCI2BXUYEXDCB","created_at":"2026-07-05T10:11:59.642618+00:00"},{"alias_kind":"pith_short_8","alias_value":"PV3XCI2B","created_at":"2026-07-05T10:11:59.642618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.05663","citing_title":"Random Walk Learning and the Pac-Man Attack","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PV3XCI2BXUYEXDCBYY55UINWZD","json":"https://pith.science/pith/PV3XCI2BXUYEXDCBYY55UINWZD.json","graph_json":"https://pith.science/api/pith-number/PV3XCI2BXUYEXDCBYY55UINWZD/graph.json","events_json":"https://pith.science/api/pith-number/PV3XCI2BXUYEXDCBYY55UINWZD/events.json","paper":"https://pith.science/paper/PV3XCI2B"},"agent_actions":{"view_html":"https://pith.science/pith/PV3XCI2BXUYEXDCBYY55UINWZD","download_json":"https://pith.science/pith/PV3XCI2BXUYEXDCBYY55UINWZD.json","view_paper":"https://pith.science/paper/PV3XCI2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11762&json=true","fetch_graph":"https://pith.science/api/pith-number/PV3XCI2BXUYEXDCBYY55UINWZD/graph.json","fetch_events":"https://pith.science/api/pith-number/PV3XCI2BXUYEXDCBYY55UINWZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PV3XCI2BXUYEXDCBYY55UINWZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PV3XCI2BXUYEXDCBYY55UINWZD/action/storage_attestation","attest_author":"https://pith.science/pith/PV3XCI2BXUYEXDCBYY55UINWZD/action/author_attestation","sign_citation":"https://pith.science/pith/PV3XCI2BXUYEXDCBYY55UINWZD/action/citation_signature","submit_replication":"https://pith.science/pith/PV3XCI2BXUYEXDCBYY55UINWZD/action/replication_record"}},"created_at":"2026-07-05T10:11:59.642618+00:00","updated_at":"2026-07-05T10:11:59.642618+00:00"}