{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OIXRQ3F6N4UCQ25GV63UCZPVC7","short_pith_number":"pith:OIXRQ3F6","schema_version":"1.0","canonical_sha256":"722f186cbe6f28286ba6afb74165f517c966a1dde740f3923943e287855674bf","source":{"kind":"arxiv","id":"2406.10976","version":1},"attestation_state":"computed","paper":{"title":"Promoting Data and Model Privacy in Federated Learning through Quantized LoRA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR"],"primary_cat":"cs.LG","authors_text":"Cenyuan Zhang, Changze Lv, Jianhao Zhu, Muling Wu, Tianlong Li, Wenhao Liu, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang, Zixuan Ling","submitted_at":"2024-06-16T15:23:07Z","abstract_excerpt":"Conventional federated learning primarily aims to secure the privacy of data distributed across multiple edge devices, with the global model dispatched to edge devices for parameter updates during the learning process. However, the development of large language models (LLMs) requires substantial data and computational resources, rendering them valuable intellectual properties for their developers and owners. To establish a mechanism that protects both data and model privacy in a federated learning context, we introduce a method that just needs to distribute a quantized version of the model's p"},"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":"2406.10976","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-16T15:23:07Z","cross_cats_sorted":["cs.CL","cs.CR"],"title_canon_sha256":"be11b9542200260f08023797985d19ba3d5994581fccda3f888bf7daf20ef8db","abstract_canon_sha256":"9f7bd594a8c7f7415d4e490a8011394f6c5c378d0849836b1d6b573de37169cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:47.125794Z","signature_b64":"xhhJDqn8b9BFNTXSuqR3nDVwfIi25gsYm1OkABRBn1Tiie0dge9zo4CBoI/L9F2X+5LMh8LzvADZhZ6yJdTRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"722f186cbe6f28286ba6afb74165f517c966a1dde740f3923943e287855674bf","last_reissued_at":"2026-07-05T08:32:47.125133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:47.125133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Promoting Data and Model Privacy in Federated Learning through Quantized LoRA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR"],"primary_cat":"cs.LG","authors_text":"Cenyuan Zhang, Changze Lv, Jianhao Zhu, Muling Wu, Tianlong Li, Wenhao Liu, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang, Zixuan Ling","submitted_at":"2024-06-16T15:23:07Z","abstract_excerpt":"Conventional federated learning primarily aims to secure the privacy of data distributed across multiple edge devices, with the global model dispatched to edge devices for parameter updates during the learning process. However, the development of large language models (LLMs) requires substantial data and computational resources, rendering them valuable intellectual properties for their developers and owners. To establish a mechanism that protects both data and model privacy in a federated learning context, we introduce a method that just needs to distribute a quantized version of the model's p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10976","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/2406.10976/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":"2406.10976","created_at":"2026-07-05T08:32:47.125214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10976v1","created_at":"2026-07-05T08:32:47.125214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10976","created_at":"2026-07-05T08:32:47.125214+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIXRQ3F6N4UC","created_at":"2026-07-05T08:32:47.125214+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIXRQ3F6N4UCQ25G","created_at":"2026-07-05T08:32:47.125214+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIXRQ3F6","created_at":"2026-07-05T08:32:47.125214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18911","citing_title":"Enhancing Model Privacy in Federated Learning with Random Masking and Quantization","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OIXRQ3F6N4UCQ25GV63UCZPVC7","json":"https://pith.science/pith/OIXRQ3F6N4UCQ25GV63UCZPVC7.json","graph_json":"https://pith.science/api/pith-number/OIXRQ3F6N4UCQ25GV63UCZPVC7/graph.json","events_json":"https://pith.science/api/pith-number/OIXRQ3F6N4UCQ25GV63UCZPVC7/events.json","paper":"https://pith.science/paper/OIXRQ3F6"},"agent_actions":{"view_html":"https://pith.science/pith/OIXRQ3F6N4UCQ25GV63UCZPVC7","download_json":"https://pith.science/pith/OIXRQ3F6N4UCQ25GV63UCZPVC7.json","view_paper":"https://pith.science/paper/OIXRQ3F6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10976&json=true","fetch_graph":"https://pith.science/api/pith-number/OIXRQ3F6N4UCQ25GV63UCZPVC7/graph.json","fetch_events":"https://pith.science/api/pith-number/OIXRQ3F6N4UCQ25GV63UCZPVC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIXRQ3F6N4UCQ25GV63UCZPVC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIXRQ3F6N4UCQ25GV63UCZPVC7/action/storage_attestation","attest_author":"https://pith.science/pith/OIXRQ3F6N4UCQ25GV63UCZPVC7/action/author_attestation","sign_citation":"https://pith.science/pith/OIXRQ3F6N4UCQ25GV63UCZPVC7/action/citation_signature","submit_replication":"https://pith.science/pith/OIXRQ3F6N4UCQ25GV63UCZPVC7/action/replication_record"}},"created_at":"2026-07-05T08:32:47.125214+00:00","updated_at":"2026-07-05T08:32:47.125214+00:00"}