{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HOBKKVZZ7C7XWAT4ZQQJBDEMCT","short_pith_number":"pith:HOBKKVZZ","schema_version":"1.0","canonical_sha256":"3b82a55739f8bf7b027ccc20908c8c14fdbbeceef5d5dce76d2afd64c709857b","source":{"kind":"arxiv","id":"2502.08024","version":1},"attestation_state":"computed","paper":{"title":"Initialization Matters: Unraveling the Impact of Pre-Training on Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Divyansh Jhunjhunwala, Gauri Joshi, Pranay Sharma, Zheng Xu","submitted_at":"2025-02-11T23:53:16Z","abstract_excerpt":"Initializing with pre-trained models when learning on downstream tasks is becoming standard practice in machine learning. Several recent works explore the benefits of pre-trained initialization in a federated learning (FL) setting, where the downstream training is performed at the edge clients with heterogeneous data distribution. These works show that starting from a pre-trained model can substantially reduce the adverse impact of data heterogeneity on the test performance of a model trained in a federated setting, with no changes to the standard FedAvg training algorithm. In this work, we pr"},"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":"2502.08024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T23:53:16Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"86bfadfd1053577f67923464bec34469c2842fa6995dd2806398b822dc00a5c4","abstract_canon_sha256":"0ff851becd5911e5d8cd222411f7e58ee5f5c67ad88283bc7797dafe80fabba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:13.877946Z","signature_b64":"HyA2QgJ5YDof874MFq6SjpFiJCtECyJW8ppZmygsiVQzjGQI2usdAylVpNVIBPbWzuUoDN/uRCXGmH5t4CMOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b82a55739f8bf7b027ccc20908c8c14fdbbeceef5d5dce76d2afd64c709857b","last_reissued_at":"2026-07-05T10:13:13.877407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:13.877407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Initialization Matters: Unraveling the Impact of Pre-Training on Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Divyansh Jhunjhunwala, Gauri Joshi, Pranay Sharma, Zheng Xu","submitted_at":"2025-02-11T23:53:16Z","abstract_excerpt":"Initializing with pre-trained models when learning on downstream tasks is becoming standard practice in machine learning. Several recent works explore the benefits of pre-trained initialization in a federated learning (FL) setting, where the downstream training is performed at the edge clients with heterogeneous data distribution. These works show that starting from a pre-trained model can substantially reduce the adverse impact of data heterogeneity on the test performance of a model trained in a federated setting, with no changes to the standard FedAvg training algorithm. In this work, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08024","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/2502.08024/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":"2502.08024","created_at":"2026-07-05T10:13:13.877462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08024v1","created_at":"2026-07-05T10:13:13.877462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08024","created_at":"2026-07-05T10:13:13.877462+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOBKKVZZ7C7X","created_at":"2026-07-05T10:13:13.877462+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOBKKVZZ7C7XWAT4","created_at":"2026-07-05T10:13:13.877462+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOBKKVZZ","created_at":"2026-07-05T10:13:13.877462+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/HOBKKVZZ7C7XWAT4ZQQJBDEMCT","json":"https://pith.science/pith/HOBKKVZZ7C7XWAT4ZQQJBDEMCT.json","graph_json":"https://pith.science/api/pith-number/HOBKKVZZ7C7XWAT4ZQQJBDEMCT/graph.json","events_json":"https://pith.science/api/pith-number/HOBKKVZZ7C7XWAT4ZQQJBDEMCT/events.json","paper":"https://pith.science/paper/HOBKKVZZ"},"agent_actions":{"view_html":"https://pith.science/pith/HOBKKVZZ7C7XWAT4ZQQJBDEMCT","download_json":"https://pith.science/pith/HOBKKVZZ7C7XWAT4ZQQJBDEMCT.json","view_paper":"https://pith.science/paper/HOBKKVZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08024&json=true","fetch_graph":"https://pith.science/api/pith-number/HOBKKVZZ7C7XWAT4ZQQJBDEMCT/graph.json","fetch_events":"https://pith.science/api/pith-number/HOBKKVZZ7C7XWAT4ZQQJBDEMCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOBKKVZZ7C7XWAT4ZQQJBDEMCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOBKKVZZ7C7XWAT4ZQQJBDEMCT/action/storage_attestation","attest_author":"https://pith.science/pith/HOBKKVZZ7C7XWAT4ZQQJBDEMCT/action/author_attestation","sign_citation":"https://pith.science/pith/HOBKKVZZ7C7XWAT4ZQQJBDEMCT/action/citation_signature","submit_replication":"https://pith.science/pith/HOBKKVZZ7C7XWAT4ZQQJBDEMCT/action/replication_record"}},"created_at":"2026-07-05T10:13:13.877462+00:00","updated_at":"2026-07-05T10:13:13.877462+00:00"}