{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4O4ADOINXQ42JQWPDDUWB7WSQL","short_pith_number":"pith:4O4ADOIN","schema_version":"1.0","canonical_sha256":"e3b801b90dbc39a4c2cf18e960fed282e08e83a249f9fc821e4f4d3f5a1dfb19","source":{"kind":"arxiv","id":"2501.14644","version":2},"attestation_state":"computed","paper":{"title":"Optimizing Privacy-Utility Trade-off in Decentralized Learning with Generalized Correlated Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Angelo Rodio, Erik G. Larsson, Zheng Chen","submitted_at":"2025-01-24T17:05:00Z","abstract_excerpt":"Decentralized learning enables distributed agents to collaboratively train a shared machine learning model without a central server, through local computation and peer-to-peer communication. Although each agent retains its dataset locally, sharing local models can still expose private information about the local training datasets to adversaries. To mitigate privacy attacks, a common strategy is to inject random artificial noise at each agent before exchanging local models between neighbors. However, this often leads to utility degradation due to the negative effects of cumulated artificial noi"},"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":"2501.14644","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T17:05:00Z","cross_cats_sorted":["cs.AI","cs.CR","cs.DC"],"title_canon_sha256":"d4bfed7a7da9204718b36352c3c2389b381761bd4907cbfa59370aed04ced461","abstract_canon_sha256":"d5e4dd2e2a51b3a8aeba0bd840ac1f2f311e81a8698966fdea3939e3e7cf5945"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:38.546536Z","signature_b64":"xylESpt6FBt8qnaL6XO49zJi8ciMZg3bidRXNmRAgrUjr0cHujWdgvwRJjOFMGPx4gRijRK9L4u/n07MnYfdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3b801b90dbc39a4c2cf18e960fed282e08e83a249f9fc821e4f4d3f5a1dfb19","last_reissued_at":"2026-07-05T11:41:38.546011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:38.546011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Privacy-Utility Trade-off in Decentralized Learning with Generalized Correlated Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Angelo Rodio, Erik G. Larsson, Zheng Chen","submitted_at":"2025-01-24T17:05:00Z","abstract_excerpt":"Decentralized learning enables distributed agents to collaboratively train a shared machine learning model without a central server, through local computation and peer-to-peer communication. Although each agent retains its dataset locally, sharing local models can still expose private information about the local training datasets to adversaries. To mitigate privacy attacks, a common strategy is to inject random artificial noise at each agent before exchanging local models between neighbors. However, this often leads to utility degradation due to the negative effects of cumulated artificial noi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14644","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/2501.14644/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":"2501.14644","created_at":"2026-07-05T11:41:38.546069+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14644v2","created_at":"2026-07-05T11:41:38.546069+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14644","created_at":"2026-07-05T11:41:38.546069+00:00"},{"alias_kind":"pith_short_12","alias_value":"4O4ADOINXQ42","created_at":"2026-07-05T11:41:38.546069+00:00"},{"alias_kind":"pith_short_16","alias_value":"4O4ADOINXQ42JQWP","created_at":"2026-07-05T11:41:38.546069+00:00"},{"alias_kind":"pith_short_8","alias_value":"4O4ADOIN","created_at":"2026-07-05T11:41:38.546069+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07565","citing_title":"Coding-Enforced Robust Secure Aggregation for Federated Learning Under Unreliable Communication","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4O4ADOINXQ42JQWPDDUWB7WSQL","json":"https://pith.science/pith/4O4ADOINXQ42JQWPDDUWB7WSQL.json","graph_json":"https://pith.science/api/pith-number/4O4ADOINXQ42JQWPDDUWB7WSQL/graph.json","events_json":"https://pith.science/api/pith-number/4O4ADOINXQ42JQWPDDUWB7WSQL/events.json","paper":"https://pith.science/paper/4O4ADOIN"},"agent_actions":{"view_html":"https://pith.science/pith/4O4ADOINXQ42JQWPDDUWB7WSQL","download_json":"https://pith.science/pith/4O4ADOINXQ42JQWPDDUWB7WSQL.json","view_paper":"https://pith.science/paper/4O4ADOIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14644&json=true","fetch_graph":"https://pith.science/api/pith-number/4O4ADOINXQ42JQWPDDUWB7WSQL/graph.json","fetch_events":"https://pith.science/api/pith-number/4O4ADOINXQ42JQWPDDUWB7WSQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4O4ADOINXQ42JQWPDDUWB7WSQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4O4ADOINXQ42JQWPDDUWB7WSQL/action/storage_attestation","attest_author":"https://pith.science/pith/4O4ADOINXQ42JQWPDDUWB7WSQL/action/author_attestation","sign_citation":"https://pith.science/pith/4O4ADOINXQ42JQWPDDUWB7WSQL/action/citation_signature","submit_replication":"https://pith.science/pith/4O4ADOINXQ42JQWPDDUWB7WSQL/action/replication_record"}},"created_at":"2026-07-05T11:41:38.546069+00:00","updated_at":"2026-07-05T11:41:38.546069+00:00"}