{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CUDBGRGIYWU5DPTGD7VFEPSOBE","short_pith_number":"pith:CUDBGRGI","schema_version":"1.0","canonical_sha256":"15061344c8c5a9d1be661fea523e4e093f3dee9c6943da7fba0149592fac485c","source":{"kind":"arxiv","id":"2503.02154","version":1},"attestation_state":"computed","paper":{"title":"AugFL: Augmenting Federated Learning with Pretrained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Junshan Zhang, Ju Ren, Sheng Yue, Yaoxue Zhang, Yongheng Deng, Zerui Qin","submitted_at":"2025-03-04T00:37:33Z","abstract_excerpt":"Federated Learning (FL) has garnered widespread interest in recent years. However, owing to strict privacy policies or limited storage capacities of training participants such as IoT devices, its effective deployment is often impeded by the scarcity of training data in practical decentralized learning environments. In this paper, we study enhancing FL with the aid of (large) pre-trained models (PMs), that encapsulate wealthy general/domain-agnostic knowledge, to alleviate the data requirement in conducting FL from scratch. Specifically, we consider a networked FL system formed by a central ser"},"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":"2503.02154","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T00:37:33Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"beeb07fb27edceceb5a9050b876ad7e2c6be530783ea11dbf734140603c8239a","abstract_canon_sha256":"07ce080b7e1ff9c1fd9b243b83b947245f68705a4d6cd9885a2f2c68a6e59d61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:37.852451Z","signature_b64":"YiwnINTy4B3DaKQzvL3OFH4VebUPDFY2NWo5l4L/99NC4KendIRl0awh4orhS1a5aN1Tupz8sD3ceUHU4J93Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15061344c8c5a9d1be661fea523e4e093f3dee9c6943da7fba0149592fac485c","last_reissued_at":"2026-07-05T10:23:37.851585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:37.851585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AugFL: Augmenting Federated Learning with Pretrained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Junshan Zhang, Ju Ren, Sheng Yue, Yaoxue Zhang, Yongheng Deng, Zerui Qin","submitted_at":"2025-03-04T00:37:33Z","abstract_excerpt":"Federated Learning (FL) has garnered widespread interest in recent years. However, owing to strict privacy policies or limited storage capacities of training participants such as IoT devices, its effective deployment is often impeded by the scarcity of training data in practical decentralized learning environments. In this paper, we study enhancing FL with the aid of (large) pre-trained models (PMs), that encapsulate wealthy general/domain-agnostic knowledge, to alleviate the data requirement in conducting FL from scratch. Specifically, we consider a networked FL system formed by a central ser"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02154","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/2503.02154/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":"2503.02154","created_at":"2026-07-05T10:23:37.851743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02154v1","created_at":"2026-07-05T10:23:37.851743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02154","created_at":"2026-07-05T10:23:37.851743+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUDBGRGIYWU5","created_at":"2026-07-05T10:23:37.851743+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUDBGRGIYWU5DPTG","created_at":"2026-07-05T10:23:37.851743+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUDBGRGI","created_at":"2026-07-05T10:23:37.851743+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10430","citing_title":"Efficient Federated Learning with Heterogeneous Data and Adaptive Dropout","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUDBGRGIYWU5DPTGD7VFEPSOBE","json":"https://pith.science/pith/CUDBGRGIYWU5DPTGD7VFEPSOBE.json","graph_json":"https://pith.science/api/pith-number/CUDBGRGIYWU5DPTGD7VFEPSOBE/graph.json","events_json":"https://pith.science/api/pith-number/CUDBGRGIYWU5DPTGD7VFEPSOBE/events.json","paper":"https://pith.science/paper/CUDBGRGI"},"agent_actions":{"view_html":"https://pith.science/pith/CUDBGRGIYWU5DPTGD7VFEPSOBE","download_json":"https://pith.science/pith/CUDBGRGIYWU5DPTGD7VFEPSOBE.json","view_paper":"https://pith.science/paper/CUDBGRGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02154&json=true","fetch_graph":"https://pith.science/api/pith-number/CUDBGRGIYWU5DPTGD7VFEPSOBE/graph.json","fetch_events":"https://pith.science/api/pith-number/CUDBGRGIYWU5DPTGD7VFEPSOBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUDBGRGIYWU5DPTGD7VFEPSOBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUDBGRGIYWU5DPTGD7VFEPSOBE/action/storage_attestation","attest_author":"https://pith.science/pith/CUDBGRGIYWU5DPTGD7VFEPSOBE/action/author_attestation","sign_citation":"https://pith.science/pith/CUDBGRGIYWU5DPTGD7VFEPSOBE/action/citation_signature","submit_replication":"https://pith.science/pith/CUDBGRGIYWU5DPTGD7VFEPSOBE/action/replication_record"}},"created_at":"2026-07-05T10:23:37.851743+00:00","updated_at":"2026-07-05T10:23:37.851743+00:00"}