{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IWM3RNW6CYWW5XZI7OZQDA6LPR","short_pith_number":"pith:IWM3RNW6","schema_version":"1.0","canonical_sha256":"4599b8b6de162d6edf28fbb30183cb7c74d7a2c94c2c3cfdff20ddb5bfd1fa6e","source":{"kind":"arxiv","id":"2206.15387","version":3},"attestation_state":"computed","paper":{"title":"Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jianyu Wang, John Nguyen, Kshitiz Malik, Maziar Sanjabi, Michael Rabbat","submitted_at":"2022-06-30T16:18:21Z","abstract_excerpt":"An oft-cited challenge of federated learning is the presence of heterogeneity. \\emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \\emph{System heterogeneity} refers to client devices having different system capabilities. A considerable number of federated optimization methods address this challenge. In the literature, empirical evaluations usually start federated training from random initialization. However, in many practical applications of federated learning, the server has access to proxy data for the training task that can"},"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":"2206.15387","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-30T16:18:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea2eb7d72951b7262e28c3af7102cf8cd7e75f9d3969728533bcb31613db0b43","abstract_canon_sha256":"f2856798dea46706ef1d4b8e1d36ac5e218d3dcc06740dd33fcd785bde3d1e77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:29.598035Z","signature_b64":"eB7lDBTnzgJqcLGPCvN5loAp6DEDrHWcCYlFrLr8l5a5AoVLp9eVoOShqFecYCWXVmdf33EZY3z4crcgdRilBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4599b8b6de162d6edf28fbb30183cb7c74d7a2c94c2c3cfdff20ddb5bfd1fa6e","last_reissued_at":"2026-07-05T05:54:29.597549Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:29.597549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jianyu Wang, John Nguyen, Kshitiz Malik, Maziar Sanjabi, Michael Rabbat","submitted_at":"2022-06-30T16:18:21Z","abstract_excerpt":"An oft-cited challenge of federated learning is the presence of heterogeneity. \\emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \\emph{System heterogeneity} refers to client devices having different system capabilities. A considerable number of federated optimization methods address this challenge. In the literature, empirical evaluations usually start federated training from random initialization. However, in many practical applications of federated learning, the server has access to proxy data for the training task that can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15387","kind":"arxiv","version":3},"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/2206.15387/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":"2206.15387","created_at":"2026-07-05T05:54:29.597613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.15387v3","created_at":"2026-07-05T05:54:29.597613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15387","created_at":"2026-07-05T05:54:29.597613+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWM3RNW6CYWW","created_at":"2026-07-05T05:54:29.597613+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWM3RNW6CYWW5XZI","created_at":"2026-07-05T05:54:29.597613+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWM3RNW6","created_at":"2026-07-05T05:54:29.597613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07565","citing_title":"Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IWM3RNW6CYWW5XZI7OZQDA6LPR","json":"https://pith.science/pith/IWM3RNW6CYWW5XZI7OZQDA6LPR.json","graph_json":"https://pith.science/api/pith-number/IWM3RNW6CYWW5XZI7OZQDA6LPR/graph.json","events_json":"https://pith.science/api/pith-number/IWM3RNW6CYWW5XZI7OZQDA6LPR/events.json","paper":"https://pith.science/paper/IWM3RNW6"},"agent_actions":{"view_html":"https://pith.science/pith/IWM3RNW6CYWW5XZI7OZQDA6LPR","download_json":"https://pith.science/pith/IWM3RNW6CYWW5XZI7OZQDA6LPR.json","view_paper":"https://pith.science/paper/IWM3RNW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.15387&json=true","fetch_graph":"https://pith.science/api/pith-number/IWM3RNW6CYWW5XZI7OZQDA6LPR/graph.json","fetch_events":"https://pith.science/api/pith-number/IWM3RNW6CYWW5XZI7OZQDA6LPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWM3RNW6CYWW5XZI7OZQDA6LPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWM3RNW6CYWW5XZI7OZQDA6LPR/action/storage_attestation","attest_author":"https://pith.science/pith/IWM3RNW6CYWW5XZI7OZQDA6LPR/action/author_attestation","sign_citation":"https://pith.science/pith/IWM3RNW6CYWW5XZI7OZQDA6LPR/action/citation_signature","submit_replication":"https://pith.science/pith/IWM3RNW6CYWW5XZI7OZQDA6LPR/action/replication_record"}},"created_at":"2026-07-05T05:54:29.597613+00:00","updated_at":"2026-07-05T05:54:29.597613+00:00"}