{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4ZX3BY4SOEW7JG7ZO7JJWSZX2Y","short_pith_number":"pith:4ZX3BY4S","schema_version":"1.0","canonical_sha256":"e66fb0e392712df49bf977d29b4b37d63575b7f471860c8d4ab7d426ff6694d0","source":{"kind":"arxiv","id":"2411.07806","version":2},"attestation_state":"computed","paper":{"title":"Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","eess.SP"],"primary_cat":"cs.LG","authors_text":"Hengtao He, Jun Zhang, Khaled B. Letaief, Shenghui Song, Tianqu Kang, Zixin Wang","submitted_at":"2024-11-12T14:01:08Z","abstract_excerpt":"Fine-tuning large pre-trained foundation models (FMs) on distributed edge devices presents considerable computational and privacy challenges. Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating collaborative model training without the need to share raw data. To lessen the computational burden on resource-limited devices, combining low-rank adaptation (LoRA) with federated learning enables parameter-efficient fine-tuning. Additionally, the split FedFT architecture partitions an FM between edge devices and a central server, reducing the necessity for complete model deploy"},"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":"2411.07806","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-12T14:01:08Z","cross_cats_sorted":["cs.CR","eess.SP"],"title_canon_sha256":"ec9ace684a1e167c97bcda091676679ea385412cc0e5eec8b2b21040b82aa13a","abstract_canon_sha256":"9dbf254fecf19d632d346220a08f9694aa440fdac3b32f200bd79fd833176e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:03.479973Z","signature_b64":"WSxGhbsULp8WoRQR+Yml/MPp/Bh2UQEAmB50tYXHfsOjspkauy3NuK3sZhMIgtq+gOAeJRMzbM5BQqEZcOOrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e66fb0e392712df49bf977d29b4b37d63575b7f471860c8d4ab7d426ff6694d0","last_reissued_at":"2026-07-05T09:41:03.479524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:03.479524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","eess.SP"],"primary_cat":"cs.LG","authors_text":"Hengtao He, Jun Zhang, Khaled B. Letaief, Shenghui Song, Tianqu Kang, Zixin Wang","submitted_at":"2024-11-12T14:01:08Z","abstract_excerpt":"Fine-tuning large pre-trained foundation models (FMs) on distributed edge devices presents considerable computational and privacy challenges. Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating collaborative model training without the need to share raw data. To lessen the computational burden on resource-limited devices, combining low-rank adaptation (LoRA) with federated learning enables parameter-efficient fine-tuning. Additionally, the split FedFT architecture partitions an FM between edge devices and a central server, reducing the necessity for complete model deploy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07806","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/2411.07806/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":"2411.07806","created_at":"2026-07-05T09:41:03.479577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07806v2","created_at":"2026-07-05T09:41:03.479577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07806","created_at":"2026-07-05T09:41:03.479577+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZX3BY4SOEW7","created_at":"2026-07-05T09:41:03.479577+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZX3BY4SOEW7JG7Z","created_at":"2026-07-05T09:41:03.479577+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZX3BY4S","created_at":"2026-07-05T09:41:03.479577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03267","citing_title":"FedGSA: Geometry-Consistent Subspace Aggregation for Differentially Private Federated LoRA","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y","json":"https://pith.science/pith/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y.json","graph_json":"https://pith.science/api/pith-number/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y/graph.json","events_json":"https://pith.science/api/pith-number/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y/events.json","paper":"https://pith.science/paper/4ZX3BY4S"},"agent_actions":{"view_html":"https://pith.science/pith/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y","download_json":"https://pith.science/pith/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y.json","view_paper":"https://pith.science/paper/4ZX3BY4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07806&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y/action/storage_attestation","attest_author":"https://pith.science/pith/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y/action/author_attestation","sign_citation":"https://pith.science/pith/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y/action/citation_signature","submit_replication":"https://pith.science/pith/4ZX3BY4SOEW7JG7ZO7JJWSZX2Y/action/replication_record"}},"created_at":"2026-07-05T09:41:03.479577+00:00","updated_at":"2026-07-05T09:41:03.479577+00:00"}