{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M5OB4Z4S5QFRYMGULJKSB55I6S","short_pith_number":"pith:M5OB4Z4S","schema_version":"1.0","canonical_sha256":"675c1e6792ec0b1c30d45a5520f7a8f4a01fd3c672a4a902b90f3f788c3d8a02","source":{"kind":"arxiv","id":"2208.12268","version":3},"attestation_state":"computed","paper":{"title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Fangqi Li, Gongshen Liu, Haodong Zhao, Peixuan Li, Wei Du","submitted_at":"2022-08-25T15:27:41Z","abstract_excerpt":"Federated learning (FL) has enabled global model training on decentralized data in a privacy-preserving way by aggregating model updates. However, for many natural language processing (NLP) tasks that utilize pre-trained language models (PLMs) with large numbers of parameters, there are considerable communication costs associated with FL. Recently, prompt tuning, which tunes some soft prompts without modifying PLMs, has achieved excellent performance as a new learning paradigm. Therefore we want to combine the two methods and explore the effect of prompt tuning under FL. In this paper, we prop"},"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":"2208.12268","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-25T15:27:41Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"ca976dabf4bd6739cb5409afce6da3c83ffd455dbdaf9c832fc39e6a4f98b577","abstract_canon_sha256":"b3661a0c0054a66247e8188c4bccdf44f0a7e8a5694b6b6dfb6ef36fa1df1dc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:20.510376Z","signature_b64":"I/DvTOXf630FlaW3BciBMYdUktFfJrxArViie9t3NVN+m0FDAxNwENd0zXNFJBAkGfPnu3560H2fdNifG4ZNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675c1e6792ec0b1c30d45a5520f7a8f4a01fd3c672a4a902b90f3f788c3d8a02","last_reissued_at":"2026-07-05T05:35:20.509856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:20.509856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Fangqi Li, Gongshen Liu, Haodong Zhao, Peixuan Li, Wei Du","submitted_at":"2022-08-25T15:27:41Z","abstract_excerpt":"Federated learning (FL) has enabled global model training on decentralized data in a privacy-preserving way by aggregating model updates. However, for many natural language processing (NLP) tasks that utilize pre-trained language models (PLMs) with large numbers of parameters, there are considerable communication costs associated with FL. Recently, prompt tuning, which tunes some soft prompts without modifying PLMs, has achieved excellent performance as a new learning paradigm. Therefore we want to combine the two methods and explore the effect of prompt tuning under FL. In this paper, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12268","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/2208.12268/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":"2208.12268","created_at":"2026-07-05T05:35:20.509920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.12268v3","created_at":"2026-07-05T05:35:20.509920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12268","created_at":"2026-07-05T05:35:20.509920+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5OB4Z4S5QFR","created_at":"2026-07-05T05:35:20.509920+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5OB4Z4S5QFRYMGU","created_at":"2026-07-05T05:35:20.509920+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5OB4Z4S","created_at":"2026-07-05T05:35:20.509920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.11707","citing_title":"Federated Co-tuning Framework for Large and Small Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19015","citing_title":"FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5OB4Z4S5QFRYMGULJKSB55I6S","json":"https://pith.science/pith/M5OB4Z4S5QFRYMGULJKSB55I6S.json","graph_json":"https://pith.science/api/pith-number/M5OB4Z4S5QFRYMGULJKSB55I6S/graph.json","events_json":"https://pith.science/api/pith-number/M5OB4Z4S5QFRYMGULJKSB55I6S/events.json","paper":"https://pith.science/paper/M5OB4Z4S"},"agent_actions":{"view_html":"https://pith.science/pith/M5OB4Z4S5QFRYMGULJKSB55I6S","download_json":"https://pith.science/pith/M5OB4Z4S5QFRYMGULJKSB55I6S.json","view_paper":"https://pith.science/paper/M5OB4Z4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.12268&json=true","fetch_graph":"https://pith.science/api/pith-number/M5OB4Z4S5QFRYMGULJKSB55I6S/graph.json","fetch_events":"https://pith.science/api/pith-number/M5OB4Z4S5QFRYMGULJKSB55I6S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5OB4Z4S5QFRYMGULJKSB55I6S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5OB4Z4S5QFRYMGULJKSB55I6S/action/storage_attestation","attest_author":"https://pith.science/pith/M5OB4Z4S5QFRYMGULJKSB55I6S/action/author_attestation","sign_citation":"https://pith.science/pith/M5OB4Z4S5QFRYMGULJKSB55I6S/action/citation_signature","submit_replication":"https://pith.science/pith/M5OB4Z4S5QFRYMGULJKSB55I6S/action/replication_record"}},"created_at":"2026-07-05T05:35:20.509920+00:00","updated_at":"2026-07-05T05:35:20.509920+00:00"}